ConceptNet
ConceptNet joins words and short phrases with edges that carry a meaning, for example "is a", "used for", "causes", or "part of". Instead of just knowing that two words appear near each other, you get an explicit statement of how they relate, which is the kind of common-sense link people use without thinking.
The graph is built from several sources: crowdsourcing, expert-made resources, and games designed to gather knowledge as people play. It spans many languages, and you can download the full data, query it through an API, or use the associated word embeddings, numeric representations of meaning that place related words close together.
For RAG and language tasks, ConceptNet is handy when you want to reason about everyday relationships between concepts, expand a query with related ideas, or add a layer of common sense that a purely text-based system tends to miss.
Related sources
Google Knowledge Graph API
An API into Google's Knowledge Graph, the store of billions of facts about entities that powers the info panels you see beside search results. You send a name or query and get back matching entities with descriptions, types, and links. Free to use within rate limits.
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.