Google Knowledge Graph API
The Knowledge Graph Search API lets you look up entities, people, places, organisations, creative works, and more, by name or keyword. For each match it returns a short description, the entity's types, an image where available, and a score showing how well it fits your query, which makes it handy for turning a raw name into a specific, identified entity.
Access is through a standard web API with a free tier and rate limits, so it suits lookups and enrichment rather than bulk download; you cannot pull the whole graph. Results come back as structured JSON that slots easily into a pipeline.
For RAG, this is a quick way to resolve and describe entities on the fly, for example to confirm which "Jordan" a document means or to attach a short, reliable summary to an entity. If you need data you can host and query in bulk, an open knowledge base such as Wikidata is the better fit.
Related sources
ConceptNet
A multilingual common-sense knowledge graph that links words and phrases with labelled connections, such as "a cat is a pet" or "rain causes wet". It captures the everyday relationships between ideas that plain text rarely spells out.
NELL (Never-Ending Language Learner)
A machine learning system from Carnegie Mellon that has been reading the web since 2010 and building a knowledge base as it goes. It extracts beliefs, entities, and the relationships between them from text, and keeps refining them over time.
WordNet
A lexical database of English that groups nouns, verbs, adjectives, and adverbs into sets of synonyms called synsets, then links those sets by meaning. It maps how words relate, which sense means what, what is a kind of what, so software can work with meaning rather than just spelling.