| YAGO | |
|---|---|
 | |
| Developer | Max-Planck-InstituteSaarbrücken |
| Initial release | 2008 |
| Stable release | 4.5 / May 2023[1] |
| Type | Semantic Web,linked data |
| License | Creative Commons CC-BY 4.0[2] |
| Website | yago-knowledge |
| Repository | |
YAGO (Yet Another GreatOntology) is an open source[3]knowledge base developed at theMax Planck Institute for Informatics inSaarbrücken. It is automatically extracted fromWikidata andSchema.org.
YAGO4, which was released in 2020, combines data that was extracted from Wikidata with relationship designators from Schema.org.[4] The previous version of YAGO, YAGO3, had knowledge of more than 10 million entities and contained more than 120 million facts about these entities.[5] The information in YAGO3 was extracted fromWikipedia (e.g., categories, redirects, infoboxes),WordNet (e.g., synsets, hyponymy), andGeoNames.[6] The accuracy of YAGO was manually evaluated to be above 95% on a sample of facts.[7] To integrate it to thelinked data cloud, YAGO has been linked to theDBpediaontology[8] and to theSUMO ontology.[9]
YAGO3 is provided inTurtle andtsv formats. Dumps of the wholedatabase are available, as well as thematic and specialized dumps. It can also be queried through various online browsers and through aSPARQL endpoint hosted by OpenLink Software. The source code of YAGO3 is available onGitHub.
YAGO has been used in theWatson artificial intelligence system.[10]
