{"slug": "entitymap", "title": "EntityMap", "summary": "EntityMap, a proposed open standard for publishing structured entity indexes, enables AI systems to understand what a website knows by declaring entities, relationships, and evidence in a machine-readable file. The standard addresses failures in current page-level AI retrieval, where concepts are treated as separate signals, publisher identity is lost, and relationships remain buried in prose. By publishing an `entitymap.json` file at a predictable URL, publishers can give AI systems structured awareness of their entities and their connections.", "body_md": "Open standard · Technical specification\n\nEntityMap is a proposed open standard for publishing a structured, entity-first index of website knowledge for AI systems, retrieval pipelines, and language-model-based applications.\n\nWhere `sitemap.xml`\n\ntells crawlers what pages exist, `entitymap.json`\n\ntells AI systems what a site knows — which entities it covers, how they relate, and where the evidence is.\n\nAI retrieval systems today operate at the page level — fetching HTML and extracting passages without structured awareness of entities, publisher identity, or concept relationships. This produces three recurring failures for publishers.\n\nThe same concept under different surface forms is treated as separate signals rather than one entity.\n\nPublisher identity is absent from retrieved content and does not survive aggregation into AI answers.\n\nConnections between concepts are buried in prose rather than declared as explicit, typed relations.\n\nEntityMap addresses these by giving publishers a standard way to declare their entities, evidence, and relationships in a machine-readable file at a predictable URL. [Read the full rationale →](why)\n\nAn EntityMap consists of two files published at predictable root-level URLs:\n\n```\nhttps://yourdomain.com/entitymap.json   ← machine-readable primary file\nhttps://yourdomain.com/entitymap.html   ← crawler and human readable view\n```\n\nA minimal entity entry:\n\n```\n{\n  \"entityId\": \"e_001\",\n  \"@type\": \"DefinedTerm\",\n  \"name\": \"Companion Planting\",\n  \"description\": \"The practice of growing different plants in proximity\n    for mutual benefit — pest control, pollination, improved yield.\",\n  \"sameAs\": \"https://www.wikidata.org/wiki/Q905413\",\n  \"relations\": [\n    { \"predicate\": \"IMPROVES\", \"targetId\": \"e_002\", \"targetName\": \"Crop Yield\" }\n  ],\n  \"hasChunks\": [\n    {\n      \"chunkId\": \"c_001\",\n      \"text\": \"Companion planting pairs plants that benefit each other —\n        growing basil near tomatoes repels aphids and improves flavour.\",\n      \"sourceUrl\": \"https://acmegardens.com/companion-planting-guide\",\n      \"pageTitle\": \"The Complete Companion Planting Guide\",\n      \"publisher\": \"Acme Gardens\",\n      \"retrieved\": \"2026-03-27T09:14:00Z\",\n      \"relevanceScore\": 0.95\n    }\n  ]\n}\n```\n\n[Full specification →](spec/v0.2) · [Minimal valid example →](spec/v0.2#appendix-a) · [Implementation guide →](how)", "url": "https://wpnews.pro/news/entitymap", "canonical_source": "https://entitymap.org/", "published_at": "2026-05-29 15:58:24+00:00", "updated_at": "2026-05-29 16:19:41.329315+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-infrastructure", "ai-tools", "ai-research"], "entities": ["EntityMap"], "alternates": {"html": "https://wpnews.pro/news/entitymap", "markdown": "https://wpnews.pro/news/entitymap.md", "text": "https://wpnews.pro/news/entitymap.txt", "jsonld": "https://wpnews.pro/news/entitymap.jsonld"}}