Knowledge graph: definition

A knowledge graph stores facts as connected entities and relationships, letting a system answer questions by following links between things rather than matching text.

Instead of a pile of documents, a knowledge graph records that "Company A acquired Company B in 2024" as a structured link between entities. That lets a system reason over relationships: who owns what, what connects to what.

Paired with language models, knowledge graphs can make answers more precise and verifiable, because the facts are structured and traceable rather than inferred from prose. They are a strong fit where accuracy and relationships matter.

Related terms

Knowledge base: A knowledge base is the curated collection of documents an AI system draws on to answer questions, and keeping it accurate and current is what keeps the answers accurate and current.
Retrieval-augmented generation (RAG): Retrieval-augmented generation is a technique that fetches relevant passages from your own documents at question time and hands them to the model, so its answer is grounded in your data instead of its training.
Grounding: Grounding is tying a model’s answer to a verifiable source, such as your documents or live data, so it reports facts instead of inventing them.