Entity
A distinct, uniquely identifiable thing — a person, place, organisation, product or concept — that a search engine can reason about…
ContentKG
Knowledge Graph
Google's database of entities and the relationships between them, used to disambiguate queries, power knowledge panels and ground generative answers.
In full
Launched in 2012, the Knowledge Graph draws on structured sources such as Wikipedia and Wikidata, licensed data, verified feeds and extraction from the open web. Entities carry stable machine identifiers (KGMIDs) that surface in some Google APIs. Inclusion is not something a site can request directly; it is earned through consistent, corroborated presence across sources the graph already trusts, and can be nudged with accurate structured data.
Example
Searching a well-known author's name returns a panel with their birth date, books and related authors assembled from graph relationships.
Related terms
Knowledge panel
An information box about an entity — person, organisation, place, work — assembled from the Knowledge Graph and shown beside or above…
Semantic search
Retrieval based on the meaning of a query and documents rather than literal keyword matching, using entities, context and learned…
Schema.org
A collaborative vocabulary of types and properties for structured data on the web, founded by Google, Microsoft, Yahoo and Yandex in 2011.
Grounding
Constraining a language model's output to information retrieved from a specified source — a search index, a document set or a database —…
Where to read more
- Wikimedia Downloads (Wikipedia Dumps) · Dataset · dumps.wikimedia.org