Knowledge Graph
Google's database of entities and the relationships between them, used to disambiguate queries, power knowledge panels and ground…
ContentNamed entity
Entity
A distinct, uniquely identifiable thing — a person, place, organisation, product or concept — that a search engine can reason about independently of the words used to name it.
In full
Search engines maintain entity graphs (Google's is the Knowledge Graph) in which entities have identifiers, attributes and relationships. Working with entities rather than strings is what lets an engine understand that 'Apple' the company differs from the fruit, and to answer questions by traversing relationships. For site owners the practical work is making your own entity unambiguous: consistent naming, Organization and Person markup, `sameAs` links to authoritative profiles, and coverage on third-party sources the graph already trusts.
Example
A consultancy links its Organization markup via `sameAs` to its Wikidata item, LinkedIn page and Companies House record.
Related terms
Semantic search
Retrieval based on the meaning of a query and documents rather than literal keyword matching, using entities, context and learned…
Knowledge panel
An information box about an entity — person, organisation, place, work — assembled from the Knowledge Graph and shown beside or above…
Schema.org
A collaborative vocabulary of types and properties for structured data on the web, founded by Google, Microsoft, Yahoo and Yandex in 2011.
Brand mention monitoring
Tracking where a brand is named across the web and inside AI answers, including whether the description is accurate and the sentiment…
Where to read more
- Wikimedia Downloads (Wikipedia Dumps) · Dataset · dumps.wikimedia.org