Skip to content
Citable

Definition

Entity

An entity is a uniquely identifiable thing — a person, organisation, product, place or concept — that exists independently of the words used to name it. Search engines and language models resolve text to entities so that 'Apple', 'Apple Inc.' and 'AAPL' map to one node, and they judge a page partly by which entities it mentions and how unambiguously it names them.

The word entered search vocabulary in May 2012, when Google announced its Knowledge Graph with the phrase "things, not strings". The point was that a query is about a thing in the world, not a sequence of characters, and that a search engine should model the thing.

Answer engines inherit that model twice over. At retrieval time, a passage that contains the entities in the question — named the way the question names them — scores higher than one that refers to them obliquely. At generation time, the language model has to decide which Mercury, which Cambridge, which Apple a passage is about; if it cannot, it either skips the passage or attributes your claim to the wrong thing.

Structured data is the cheapest way to remove that doubt. This site describes its author and publisher as entities with stable identifiers, following the pattern in Structured data for AI answers:

json
{
  "@type": "Organization",
  "@id": "https://example.com/#organization",
  "name": "Example Ltd",
  "sameAs": [
    "https://www.wikidata.org/wiki/Q000000",
    "https://www.linkedin.com/company/example"
  ]
}

Every glossary term here is emitted as a DefinedTerm for the same reason: one page, one entity, one unambiguous name.

Frequently asked questions

How do I make an entity unambiguous on a page?

Use the full name on first mention, put the abbreviation in parentheses, and stay consistent afterwards instead of switching to 'it' or a nickname. Then give the entity machine-readable identity: an Organization, Person or DefinedTerm object in JSON-LD with a stable @id and sameAs links to the same thing on Wikidata, Wikipedia or an official profile.

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

    How to write answer-first content that LLMs can quote

    Answer-first content opens every page and every section with a self-contained answer of roughly 40–70 words, then explains, qualifies and expands. The first sentence names the main entity, each heading carries exactly one question, and no passage depends on a pronoun or a paragraph elsewhere. Written this way, a passage still makes sense after an answer engine splits the page into chunks and retrieves one of them in isolation.

    8 min read