Skip to content
Citable

Definition

Knowledge graph

A knowledge graph is a structured database of entities — people, organisations, places, products, concepts — and the typed relationships between them, such as founded by, located in or is a subtype of. Search engines and answer engines use one to disambiguate names, verify facts and assemble panels; Google's Knowledge Graph, introduced in 2012, and the open Wikidata project are the best-known examples.

Google announced its Knowledge Graph on 16 May 2012 with the slogan things, not strings, seeded from Freebase, Wikipedia and the CIA World Factbook. Wikidata, the open knowledge graph maintained by the Wikimedia community, launched later the same year and is now the identifier most other systems link to. Google also exposes a Knowledge Graph Search API that returns entities as schema.org JSON-LD, which is a useful way to check whether a name resolves to anything at all.

For answer engines the graph is a source of corroboration. A language model that can resolve your company, your author and your product to known entities can attach your claims to them, judge whether you are a plausible authority, and avoid confusing you with a namesake. A name that resolves to nothing has to be taken on trust, which retrieval systems are designed not to do.

Sites do not write to a knowledge graph directly; they make it easy for one to read them. The pattern in Structured data for AI answers is a Person or Organization object with a stable @id and sameAs links:

json
{
  "@type": "Person",
  "@id": "https://example.com/authors/jane-doe#person",
  "name": "Jane Doe",
  "sameAs": ["https://www.wikidata.org/wiki/Q000000", "https://github.com/janedoe"]
}

Frequently asked questions

How does an organisation or author get into a knowledge graph?

Mostly by being consistently described in sources the graph already trusts: a Wikipedia article and Wikidata item where the notability threshold is met, official profiles, and a home page whose Organization or Person JSON-LD links all of those with sameAs. Consistency of name, logo, founding date and description across those sources is what lets the graph merge them into one entity.

Related terms

Guides that use this term

  • Structured data

    Structured data for AI answers: the schema.org types that matter

    Structured data for AI answers is JSON-LD that labels what a page contains: Article or TechArticle for provenance (author, datePublished, dateModified, citation), FAQPage for question–answer pairs, DefinedTerm for definitions, Person with sameAs for authors, BreadcrumbList and WebSite for context, and SpeakableSpecification for the direct answer. Google requires no markup for AI features; its value is removing ambiguity, so generate it from the CMS fields that render the visible text.

    9 min read

  • Content

    E-E-A-T for answer engines: authors, dates and sources that machines can verify

    E-E-A-T (Experience, Expertise, Authoritativeness, Trustworthiness) is Google's description of a reliable source, and it is not a ranking factor. For answer engines it translates into signals a machine can verify: a named author with a profile page and Person markup, visible published and updated dates that match the structured data, outbound links to primary sources with a citation list, first-hand evidence, and an About page that says who is responsible.

    8 min read