YAGO (Yet Another Great Ontology) blends three sources to get both breadth and quality: Wikipedia for facts about entities, WordNet for a clean backbone of concepts and categories, and GeoNames for places. The result is a knowledge base where entities are neatly typed and the facts have been checked for consistency, which keeps the error rate low compared with graphs built from raw text alone.
A notable feature is that many facts carry time and location, so you can capture statements such as who held an office during a given period, not just the bare relationship. The data is published as RDF triples, small subject, predicate, object statements, and you can download the dumps or query them with SPARQL, a query language built for knowledge graphs.
For RAG, YAGO is a good pick when accuracy and clean entity types matter more than sheer size, for example when you need dependable facts to check or enrich the answers your system generates.
Related sources
DBpedia
A knowledge graph built by pulling the structured parts of Wikipedia, mainly the infoboxes, into machine-readable data. It holds billions of facts about people, places, organisations, and more as RDF triples, small subject, predicate, object statements, which you can search with the SPARQL query language.
Freebase
A collaborative knowledge base once run by Google, now retired but still available as downloadable data dumps. It holds structured facts about millions of entities, and much of its content has since moved into Wikidata.
OpenCyc
The open release of Cyc, one of the oldest attempts to hand-build common-sense knowledge for machines. It holds hundreds of thousands of concepts and millions of assertions about how the everyday world fits together. Now archived, but the data is still available.
Wikidata
A free, collaborative knowledge base that holds structured facts for Wikipedia and the other Wikimedia projects. More than 100M items, each one machine-readable with statements, relationships, and identifiers, so you can pull clean facts instead of parsing article prose. Released into the public domain under CC0.