DBpedia
DBpedia turns Wikipedia's semi-structured content into a proper knowledge graph. The project extracts facts from infoboxes, categories, and links, then publishes them as RDF triples: each fact is a small statement of the form subject, predicate, object, such as "Berlin, capital of, Germany". This lets you treat encyclopaedic knowledge as data you can query rather than pages you have to read.
You can explore the data live through a SPARQL endpoint, a query language designed for knowledge graphs, or download bulk dumps to host your own copy. Because DBpedia follows Wikipedia's structure across many languages, it offers wide, general-purpose coverage and links out to other datasets in the linked open data world.
For RAG, DBpedia works well as a source of structured facts and entity relationships to sit beside your text. It predates and complements Wikidata, and the two are often used together when you want both breadth and reliable identifiers.
Related sources
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.
Wikipedia
Complete database dumps of Wikipedia and the other Wikimedia projects, in every language, refreshed roughly twice a month. The most widely used knowledge source for RAG systems, and an easy first corpus to build a retrieval pipeline on.