{{short description|Type of knowledge base}} {{other uses}} [[File:Conceptual Diagram - Example.svg|thumb|Example conceptual diagram]]
In [[knowledge representation and reasoning]], a '''knowledge graph''' is a [[knowledge base]] that uses a [[Graph (discrete mathematics)|graph]]-structured [[data model]] or [[topology]] to represent and operate on [[data]]. Knowledge graphs are often used to store interlinked descriptions of [[Named entity|entities]]{{snd}} objects, events, situations or abstract concepts{{snd}} while also encoding the free-form [[semantics]] or relationships underlying these entities.<ref>{{Cite web |date=2018 |title=What is a Knowledge Graph? |url=https://ontotext.com/knowledgehub/fundamentals/what-is-a-knowledge-graph |access-date=2025-12-05 |website=ontotext}}</ref><ref>{{Cite web |last=Kumar Pandey |first=Atul |date=2020-12-18 |title=What defines a knowledge graph? |url=https://www.atulhost.com/what-is-knowledge-graph |access-date=2025-12-05 |website=AtulHost}}</ref>
Since the development of the [[Semantic Web]], knowledge graphs have often been associated with [[linked data|linked open data]] projects, focusing on the connections between [[concept]]s and entities.<ref name="Ref1">{{cite conference|last1=Ehrlinger|first1=Lisa|last2=Wöß|first2=Wolfram|year=2016|title=Towards a Definition of Knowledge Graphs|url=http://ceur-ws.org/Vol-1695/paper4.pdf|conference=SEMANTiCS2016|location=Leipzig|publisher=Joint Proceedings of the Posters and Demos Track of 12th International Conference on Semantic Systems – SEMANTiCS2016 and 1st International Workshop on Semantic Change & Evolving Semantics (SuCCESS16)|pages=13–16}}</ref><ref>{{Cite book|last=Soylu|first=Ahmet|title=The Semantic Web – ISWC 2020 |chapter=Enhancing Public Procurement in the European Union Through Constructing and Exploiting an Integrated Knowledge Graph |date=2020|chapter-url=https://doi.org/10.1007/978-3-030-62466-8_27|series=Lecture Notes in Computer Science|volume=12507|language=en|pages=430–446|doi=10.1007/978-3-030-62466-8_27|isbn=978-3-030-62465-1|s2cid=226229398}}</ref> They are also historically associated with and used by [[search engine]]s such as [[Knowledge Graph (Google)|Google]], [[Bing (search engine)|Bing]], and [[Yahoo]]; [[knowledge engine]]s and question-answering services such as [[WolframAlpha]], Apple's [[Siri]], and [[Amazon Alexa]]; and [[social network]]s such as [[LinkedIn]] and [[Facebook]].
Recent developments in data science and [[machine learning]], particularly in [[graph neural network]]s, representation learning, and machine learning, have broadened the scope of knowledge graphs beyond their traditional use in search engines and [[recommender system]]s. They are increasingly used in scientific research, with notable applications in fields such as [[genomics]], [[proteomics]], and [[systems biology]].<ref>{{Cite journal |last1=Mohamed |first1=Sameh K. |last2=Nounu |first2=Aayah |last3=Nováček |first3=Vít |date=2021 |title=Biological applications of knowledge graph embedding models |journal=Briefings in Bioinformatics |volume=22 |issue=2 |pages=1679–1693 |doi=10.1093/bib/bbaa012 |pmid=32065227 |via=Oxford Academic|doi-access=free |hdl=1983/919db5c6-6e10-4277-9ff9-f86bbcedcee8 |hdl-access=free }}</ref>
== History == The term was coined as early as 1972 by the Austrian [[Linguistics|linguist]] [[Edgar W. Schneider]], in a discussion of how to build modular instructional systems for courses.<ref>{{cite web |last1=Schneider |first1=Edward W. |date=1973 |title=Course Modularization Applied: The Interface System and Its Implications For Sequence Control and Data Analysis. |url=https://files.eric.ed.gov/fulltext/ED088424.pdf |access-date=5 December 2025}}</ref> In the late 1980s, the [[University of Groningen]] and [[University of Twente]] jointly began a project called Knowledge Graphs, focusing on the design of [[semantic network]]s with edges restricted to a limited set of relations, to facilitate [[graph algebra|algebras on the graph]].<ref>{{Cite journal |last1=Victor |first1=Filippov |last2=Natalya |first2=Ayusheeva |last3=Maria |first3=Kusheeva |date=2024-03-17 |title=Algorithms and methods for automated construction of knowledge graphs based on text sources |url=https://www.e3s-conferences.org/articles/e3sconf/pdf/2024/61/e3sconf_uesf2024_03017.pdf |access-date=2025-08-18 |journal=E3S Web of Conferences |volume=531 |page=03017 |doi=10.1051/e3sconf/202453103017 |bibcode=2024E3SWC.53103017F }}</ref> In subsequent decades, the distinction between semantic networks and knowledge graphs was blurred.
Some early knowledge graphs were topic-specific. In 1985, [[Wordnet]] was founded, capturing semantic relationships between words and meanings{{snd}}an application of this idea to language itself. In 2005, Marc Wirk founded [[Geonames]] to capture relationships between different geographic names and locales and associated entities. In 1998, Andrew Edmonds of Science in Finance Ltd in the UK created a system called ThinkBase that offered [[Fuzzy logic|fuzzy-logic]] based reasoning in a graphical context.<ref>{{cite web |title=US Trademark no 75589756 |url=http://tmsearch.uspto.gov/bin/showfield?f=doc&state=4809:rjqm9h.2.1 |url-status=dead}}</ref>
In 2007, both [[DBpedia]] and [[Freebase (database)|Freebase]] were founded as graph-based knowledge [[Repository (version control)|repositories]] for general-purpose knowledge.<ref>{{Cite web |last1=Michael |first1=Färber |last2=Basil |first2=Ell |last3=Carsten |first3=Menne |last4=Achim |first4=Rettinger |date=2015-01-15 |title=A Comparative Survey of DBpedia, Freebase, OpenCyc, Wikidata, and YAGO |url=https://www.semantic-web-journal.net/system/files/swj1141.pdf |access-date=2025-08-18 |website=KIT}}</ref> DBpedia focused exclusively on data extracted from [[Wikipedia]], while Freebase also included a range of public datasets. Neither described themselves as a 'knowledge graph' but developed and described related concepts.
In 2012, Google introduced their [[Knowledge Graph (Google)|Knowledge Graph]],<ref name="Singhal-2012">{{Cite web|last=Singhal|first=Amit|date=May 16, 2012|title=Introducing the Knowledge Graph: things, not strings|url=https://googleblog.blogspot.com/2012/05/introducing-knowledge-graph-things-not.html|access-date=21 March 2017|website=Official Google Blog}}</ref> building on DBpedia and Freebase among other sources. They later incorporated [[RDFa]], [[Microdata (HTML)|Microdata]], [[JSON-LD]] content extracted from indexed web pages, including the ''[[The World Factbook|CIA World Factbook]]'', [[Wikidata]], and Wikipedia.<ref name="Singhal-2012" /><ref>{{cite web|last=Schwartz|first=Barry|date=December 17, 2014|title=Google's Freebase To Close After Migrating To Wikidata: Knowledge Graph Impact?|url=https://www.seroundtable.com/google-freebase-wikidata-knowledge-graph-19591.html|access-date=December 10, 2017|website=Search Engine Roundtable}}</ref> Entity and relationship types associated with this knowledge graph have been further organized using terms from the [[schema.org]]<ref name="McCusker">{{Cite web|last1=McCusker|first1=James P.|last2=McGuiness|first2=Deborah L.|title=What is a Knowledge Graph?|url=https://www.authorea.com/users/6341/articles/107281-what-is-a-knowledge-graph/_show_article|access-date=21 March 2017|website=www.authorea.com}}</ref> vocabulary. The Google Knowledge Graph became a complement to string-based search within Google, and its popularity online brought the term into more common use.<ref name="McCusker" />
Since then, several large multinationals have advertised their use of knowledge graphs, further popularising the term. These include [[Facebook]], [[LinkedIn]], [[Airbnb]], [[Microsoft]], [[Amazon.com|Amazon]], [[Uber]] and [[eBay]].<ref>{{Cite web |date=2020 |title=Knowledge Graph Enterprises |url=https://kgkg.factnexus.com/@3782~167.html |url-status=dead |access-date=2020-07-17 |archive-date=2020-07-17 |archive-url=https://web.archive.org/web/20200717063112/https://kgkg.factnexus.com/@3782~167.html }}</ref>
In 2019, [[Institute of Electrical and Electronics Engineers|IEEE]] combined its annual international conferences on "Big Knowledge" and "Data Mining and Intelligent Computing" into the International Conference on Knowledge Graph.<ref>{{Cite web|date=2017-07-09|title=2021 IEEE International Conference on Knowledge Graph (ICKG)*|url=https://kmeducationhub.de/ieee-international-conference-big-knowledge-icbk/|access-date=2021-03-22|website=KMedu Hub|language=en-US}}</ref>
The development of large language models expanded interest in knowledge graphs as a way to structure information from unstructured text, with advances in language processing enabling their automatic or semi-automatic generation and expansion.<ref>{{Citation |last1=Edge |first1=Darren |title=From Local to Global: A Graph RAG Approach to Query-Focused Summarization |date=2025-02-19 |url=http://arxiv.org/abs/2404.16130 |access-date=2025-11-20 |arxiv=2404.16130 |last2=Trinh |first2=Ha |last3=Cheng |first3=Newman |last4=Bradley |first4=Joshua |last5=Chao |first5=Alex |last6=Mody |first6=Apurva |last7=Truitt |first7=Steven |last8=Metropolitansky |first8=Dasha |last9=Ness |first9=Robert Osazuwa}}</ref><ref>{{Cite book |last1=Yih |first1=Wen-tau |last2=Chang |first2=Ming-Wei |last3=He |first3=Xiaodong |last4=Gao |first4=Jianfeng |chapter=Semantic Parsing via Staged Query Graph Generation: Question Answering with Knowledge Base |date=July 2015 |editor-last=Zong |editor-first=Chengqing |editor2-last=Strube |editor2-first=Michael |title=Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) |chapter-url=https://aclanthology.org/P15-1128/ |location=Beijing, China |publisher=Association for Computational Linguistics |pages=1321–1331 |doi=10.3115/v1/P15-1128}}</ref><ref>{{Cite journal |last1=Lewis |first1=Patrick |last2=Perez |first2=Ethan |last3=Piktus |first3=Aleksandra |last4=Petroni |first4=Fabio |last5=Karpukhin |first5=Vladimir |last6=Goyal |first6=Naman |last7=Küttler |first7=Heinrich |last8=Lewis |first8=Mike |last9=Yih |first9=Wen-tau |last10=Rocktäschel |first10=Tim |last11=Riedel |first11=Sebastian |last12=Kiela |first12=Douwe |date=2020 |title=Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks |url=https://proceedings.neurips.cc/paper/2020/hash/6b493230205f780e1bc26945df7481e5-Abstract.html |journal=Advances in Neural Information Processing Systems |publisher=Curran Associates, Inc. |volume=33 |pages=9459–9474}}</ref> The term knowledge graph has since broadened to include the dynamically constructed and adaptive graph structures, which support retrieval, reasoning, and summarization in generative systems. Microsoft Research's [https://github.com/microsoft/graphrag GraphRAG] (2024) exemplified this development by integrating LLM-generated graphs into retrieval-augmented generation.
== Definitions == There is no single commonly accepted definition of a knowledge graph. Most definitions view the topic through a Semantic Web lens and include these features:<ref>{{cite journal|last1=Hogan|first1=Aidan|last2=Blomqvist|first2=Eva|last3=Cochez|first3=Michael|last4=d'Amato|first4=Claudia|last5=de Melo|first5=Gerard|last6=Gutierrez|first6=Claudio|last7=Labra Gayo|first7=José Emilio|last8=Kirrane|first8=Sabrina|last9=Neumaier|first9=Sebastian|last10=Polleres|first10=Axel|last11=Navigli|first11=Roberto|last12=Ngonga Ngomo|first12=Axel-Cyrille|last13=Rashid|first13=Sabbir M.|last14=Rula|first14=Anisa|last15=Schmelzeisen|first15=Lukas|last16=Sequeda|first16=Juan|last17=Staab|first17=Steffen|last18=Zimmermann|first18=Antoine|date=2021-01-24|title=Knowledge Graphs|journal=ACM Computing Surveys|volume=54|issue=4|pages=1–37|doi=10.1145/3447772| issn=0360-0300|arxiv=2003.02320|s2cid=235716181}}</ref>
*''Flexible relations among knowledge in topical domains'': A knowledge graph (i) defines [[abstract class]]es and relations of entities in a schema, (ii) mainly describes real world entities and their interrelations, organized in a graph, (iii) allows for potentially interrelating arbitrary entities with each other, and (iv) covers various topical domains.<ref>{{cite journal|last1=Paulheim|first1=Heiko|date=2017|title=Knowledge Graph Refinement: A Survey of Approaches and Evaluation Methods|url=http://www.semantic-web-journal.net/system/files/swj1083.pdf|journal=Semantic Web|pages=489–508|access-date=21 March 2017}}</ref> * ''General structure'': A network of entities, their semantic types, properties, and relationships.<ref>{{cite journal|last1=Krötsch|first1=Markus|last2=Weikum|first2=Gerhard|title=Editorial of the Special Issue on Knowledge Graphs|journal=Journal of Web Semantics|date=March 2016|volume=37-38|pages=53–54|doi=10.1016/j.websem.2016.04.002|url=https://doi.org/10.1016/j.websem.2016.04.002|access-date=10 February 2021|url-access=subscription}}</ref><ref>{{Cite web|title=What is a Knowledge Graph?{{!}}Ontotext|url=https://www.ontotext.com/knowledgehub/fundamentals/what-is-a-knowledge-graph|access-date=2020-07-01|website=Ontotext|language=en-US}}</ref> To represent properties, categorical or numerical values are often used. * ''Supporting reasoning over inferred ontologies'': A knowledge graph acquires and integrates information into an ontology and applies a reasoner to derive new knowledge.<ref name="Ref1" />
There are, however, many knowledge graph representations for which some of these features are not relevant. For those knowledge graphs, this simpler definition may be more useful: * A digital structure that represents knowledge as concepts and the relationships between them (facts). A knowledge graph can include an ontology that allows both humans and machines to understand and reason about its contents.<ref>{{cite journal|last1=Peng|first1=Ciyuan|last2=Feng|first2=Xia|last3=Naseriparsa|first3=Mehdi|last4=Osborne|first4=Francesco|date=2023|title=Knowledge Graphs: Opportunities and Challenges|url=https://doi.org/10.1007/s10462-023-10465-9| journal=Artificial Intelligence Review|volume=56|issue=11 |pages=13071–13102|doi=10.1007/s10462-023-10465-9|pmid=37362886 |pmc=10068207 | issn=1573-7462|arxiv=2303.13948}}</ref><ref>{{Cite web|date=2020|title=The Knowledge Graph about Knowledge Graphs|url=https://kgkg.factnexus.com/@3782~6.html|url-status=dead|archive-url=https://web.archive.org/web/20200717054553/https://kgkg.factnexus.com/@3782~6.html|archive-date=2020-07-17}}</ref>
=== Implementations === In addition to the above examples, the term has been used to describe open knowledge projects such as [[YAGO (database)|YAGO]] and Wikidata; federations like the Linked Open Data cloud;<ref>{{Cite web|title=The Linked Open Data Cloud|url=https://lod-cloud.net/|access-date=2020-06-30|website=lod-cloud.net}}</ref> a range of commercial search tools, including Yahoo's semantic search assistant Spark, Google's [[Knowledge Graph (Google)|Knowledge Graph]], and Microsoft's Satori; and the LinkedIn and Facebook entity graphs.<ref name="Ref1" />
The term is also used in the context of [[note-taking software]] applications that allow a user to build a [[personal knowledge graph]].<ref>{{cite journal |last1=Pyne |first1=Yvette |last2=Stewart |first2=Stuart |date=March 2022 |title=Meta-work: how we research is as important as what we research |journal=[[British Journal of General Practice]] |volume=72 |issue=716 |pages=130–131 |pmid=35210247 |pmc=8884432 |doi=10.3399/bjgp22X718757}}</ref>
The popularization of knowledge graphs and their accompanying methods have led to the development of graph databases such as Neo4j,<ref>{{Cite web |title=Neo4j Graph Database & Analytics {{!}} Graph Database Management System |url=https://neo4j.com/ |access-date=8 November 2023 |website=Neo4j}}</ref> GraphDB<ref>{{Cite web |title=Ontotext GraphDB |url=https://www.ontotext.com/products/graphdb/ |access-date=8 November 2023 |website=Ontotext}}</ref> and [[AgensGraph]].<ref>{{Cite web |title=An Enterprise Graph Database Management System |url=https://bitnine.net/agensgraph/ |access-date=19 February 2025 |website=Bitnine.net}}</ref> These graph databases allow users to easily store data as entities and their interrelationships, and facilitate operations such as data reasoning, node embedding, and ontology development on knowledge bases.
In contrast, virtual knowledge graphs do not store information in specialized databases.<ref>{{Cite web |last=Sa |first=Wang |date=2025-02-07 |title=Knowledge Graph |url=https://www.puppygraph.com/blog/knowledge-graph |access-date=2025-08-18 |website=www.puppygraph.com}}</ref> They rely on an underlying relational database or data lake to answer queries on the graph. Such a virtual knowledge graph system must be properly configured in order to answer the queries correctly. This specific configuration is done through a set of mappings that define the relationship between the elements of the data source and the structure and ontology of the virtual knowledge graph.<ref>{{Cite journal |last1=Xiao |first1=Guohui |last2=Ding |first2=Linfang |last3=Cogrel |first3=Benjamin |last4=Calvanese |first4=Diego |title=Virtual Knowledge Graphs: An Overview of Systems and Use Cases |journal=Data Intelligence |date=2019 |volume=1 |issue=3 |pages=201–223 |doi=10.1162/dint_a_00011 |url=https://direct.mit.edu/dint/article/1/3/201/9978/Virtual-Knowledge-Graphs-An-Overview-of-Systems|doi-access=free }}</ref>
== Using a knowledge graph for reasoning over data == {{main|Ontology (information science)}}
A knowledge graph formally represents semantics by describing entities and their relationships.<ref>{{Cite web|date=2022-04-05|title=How do knowledge graphs work?|url=https://www.stardog.com/knowledge-graph/|access-date=2022-04-05|website=Stardog|language=en-US}}</ref> Knowledge graphs may make use of [[Ontology (information science)|ontologies]] as a schema layer. By doing this, they allow [[Inference|logical inference]] for retrieving [[implicit knowledge]] rather than only allowing queries requesting explicit knowledge.<ref>{{Cite web |date=2023-09-01 |title=Unlocking the Power of Google Knowledge Panel: How to Obtain and Claim Yours in 2023 – RH Razu |url=https://rhrazu.com/google-knowledge-panel-obtain-and-claim-yours-in-2023/ |access-date=2023-09-05 |website=rhrazu.com |language=en-US}}</ref>
In order to allow the use of knowledge graphs in various machine learning tasks, several methods for deriving latent feature representations of entities and relations have been devised.<ref>{{Cite web |last=Jens |first=Lehmann |date=2021-07-15 |title=Representation Learning in Knowledge Graphs |url=https://jens-lehmann.org/research-areas/representation-learning-in-knowledge-graphs/ |access-date=2025-08-18 |website=jens-lehmann.org}}</ref> These knowledge graph embeddings allow them to be connected to machine learning methods that require feature vectors like [[word embedding]]s. This can complement other estimates of conceptual similarity.<ref>{{Cite book|author=Hongwei Wang|title=Proceedings of the 27th ACM International Conference on Information and Knowledge Management |chapter=RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems |date=October 2018|pages=417–426|doi=10.1145/3269206.3271739|arxiv=1803.03467|isbn=9781450360142 |s2cid=3766110}}</ref><ref>{{Citation |last1=Ristoski |first1=Petar |pages=498–514 |year=2016 |last2=Paulheim |first2=Heiko |chapter=RDF2Vec: RDF Graph Embeddings for Data Mining |title=The Semantic Web – ISWC 2016 |series=Lecture Notes in Computer Science |volume=9981 |doi=10.1007/978-3-319-46523-4_30|isbn=978-3-319-46522-7 |chapter-url=https://madoc.bib.uni-mannheim.de/41307/1/Ristoski_RDF2Vec.pdf |doi-access=free }}</ref>
Models for generating useful knowledge graph embeddings are commonly the domain of graph neural networks (GNNs).<ref>{{Cite journal |last1=Zhou |first1=Jie |last2=Cui |first2=Ganqu |display-authors=1 |date=2020 |title=Graph neural networks: A review of methods and applications. |journal=AI Open |volume=1 |issue=1 |pages=57–81 |doi=10.1016/j.aiopen.2021.01.001 |s2cid=56517517 |via=Elsevier Science Direct|doi-access=free |arxiv=1812.08434 }}</ref> GNNs are deep learning architectures that comprise edges and nodes, which correspond well to the entities and relationships of knowledge graphs. The topology and data structures afforded by GNNs provide a convenient domain for semi-supervised learning, wherein the network is trained to predict the value of a node embedding (provided a group of adjacent nodes and their edges) or edge (provided a pair of nodes). These tasks serve as fundamental abstractions for more complex tasks such as knowledge graph reasoning and alignment.<ref>{{Cite journal |last1=Ye |first1=Zi |last2=Kumar |first2=Yogan Jaya |last3=Sing |first3=Goh Ong |last4=Song |first4=Fengyan |last5=Wang |first5=Junsong |date=2022 |title=A comprehensive survey of graph neural networks for knowledge graphs. |journal=IEEE Access |volume=10 |pages=75729–7574 |doi=10.1109/ACCESS.2022.3191784 |bibcode=2022IEEEA..1075729Y |s2cid=250654689 |via=IEEE Xplore|doi-access=free }}</ref>
=== Entity alignment === [[File:Knowledge graph entity alignment.png|thumb|Two hypothetical knowledge graphs representing disparate topics contain a node that corresponds to the same entity in the real world. Entity alignment is the process of identifying such nodes across multiple graphs.|upright 2]]
As new knowledge graphs are produced across a variety of fields and contexts, the same entity will inevitably be represented in multiple graphs. However, because no single standard for the construction or representation of knowledge graph exists, resolving which entities from disparate graphs correspond to the same real world subject is a non-trivial task. This task is known as ''knowledge graph entity alignment'', and is an active area of research.<ref>{{Cite conference |last1=Berrendorf |first1=Max |last2=Faerman |first2=Evgeniy |last3=Melnychuk |first3=Valentyn |last4=Tresp |first4=Volker |last5=Seidl |first5=Thomas |date=April 14–17, 2020 |title=Knowledge graph entity alignment with graph convolutional networks: lessons learned |conference=Advances in Information Retrieval: 42nd European Conference on IR Research, ECIR 2020, Lisbon, Portugal |series=Lecture Notes in Computer Science |volume=Proceedings, Part II |pages=3–11 |doi=10.1007/978-3-030-45442-5_1 |arxiv=1911.08342 |isbn=978-3-030-45441-8 |s2cid=208158314 |via=Springer International Publishing}}</ref>
Strategies for entity alignment generally seek to identify similar substructures, semantic relationships, shared attributes, or combinations of all three between two distinct knowledge graphs.<ref>{{Cite journal |last1=Zequn |first1=Sun |last2=Qingheng |first2=Zhang |last3=Wei |first3=Hu |last4=Chengming |first4=Wang |last5=Muhao |first5=Chen |last6=Farahnaz |first6=Akrami |last7=Chengkai |first7=Li |date=2020-03-26 |title=A Benchmarking Study of Embedding-based Entity Alignment for Knowledge Graphs |url=https://par.nsf.gov/servlets/purl/10302370 |access-date=2025-08-18 |journal=Proceedings of the VLDB Endowment |volume=13 |issue=12 |pages=2326–2340 |doi=10.14778/3407790.3407828 |arxiv=2003.07743 }}</ref> Entity alignment methods use these structural similarities between generally non-isomorphic graphs to predict which nodes correspond to the same entity.<ref>{{Cite arXiv |last1=Chaurasiya |first1=Deepak |last2=Surisetty |first2=Anil |last3=Kumar |first3=Nitish |last4=Singh |first4=Alok |last5=Dey |first5=Vikrant |last6=Malhotra |first6=Aakarsh |last7=Dhama |first7=Gaurav |last8=Arora |first8=Ankur |date=2022 |title=Entity alignment for knowledge graphs: progress, challenges, and empirical studies |class=cs.AI |eprint=2205.08777 }}</ref>
In 2023, researchers found success in using large language models (LLMs) in the task of entity alignment. <ref>{{Cite journal |last1=Hogan |first1=Aidan |last2=Lippolis |first2=Anna Sofia |last3=Klironomos |first3=Antonis |last4=Milon-Flores |first4=Daniela F. |last5=Zheng |first5=Heng |last6=Jouglar |first6=Alexane |last7=Norouzi |first7=Ebrahim |date=2023 |title=Enhancing Entity Alignment Between Wikidata and ArtGraph using LLMs |url=https://aidanhogan.com/docs/art_wikidata_kgs_llms.pdf |journal=Proceedings of the International Workshop on Semantic Web and Ontology Design for Cultural Heritage |via=International Workshop on Semantic Web and Ontology Design for Cultural Heritage (SWODCH), Athens, Greece}}</ref> This was in particular thanks to their effectiveness at producing syntactically meaningful embeddings. {{Citation needed|reason=Claim not supported in source above.|date=May 2026}}
As the amount of data stored in knowledge graphs grows, developing dependable methods for knowledge graph entity alignment becomes an increasingly crucial step in the integration and cohesion of knowledge graph data.
== See also ==
* {{Annotated link |Concept map}} * {{Annotated link |Formal semantics (natural language)}} * {{Annotated link |Graph database}} * {{Annotated link |Knowledge base}} * {{Annotated link |Knowledge graph embedding}} * {{Annotated link |Logical graph}} * {{Annotated link |Semantic integration}} * {{Annotated link |Semantic technology}} * {{Annotated link |Topic map}} * {{Annotated link |Vadalog}} * [[Wikibase]]- Mediawiki Software extensions for creating knowledge bases * [[Wikidata]] - Free Knowledge Database Project * {{Annotated link |YAGO (database)}}
== References == <!-- Inline citations added to your article will automatically display here. See https://en.wikipedia.org/wiki/WP:REFB for instructions on how to add citations. --> {{reflist}}
==External links== {{subject bar|d=y|auto=y}} *{{cite news|url=https://www.technologyreview.com/2020/09/04/1008156/knowledge-graph-ai-reads-web-machine-learning-natural-language-processing/ | title= This know-it-all AI learns by reading the entire web nonstop | quote=Diffbot is building the biggest-ever knowledge graph by applying image recognition and natural-language processing to billions of web pages. | work = MIT Technology Review | author = Will Douglas Heaven | date = 4 September 2020 | access-date = 5 September 2020}}
{{Scholia|topic}} {{Authority control}}
[[Category:Knowledge graphs| ]] [[Category:Ontology (information science)]] [[Category:Formal semantics (natural language)]] [[Category:Information science]]