Wikidata Entity Resolver — for AI Agents

An entity-resolution and grounding tool built for AI agents, LLMs and RAG pipelines. Resolve any person, company, place or concept to a structured Wikidata entity — its Q-ID, label, description, type, key facts and cross-database identifiers (VIAF, ISNI, ORCID, IMDb, socials, GND, and more). Exactly the "who/what is X?" lookup an agent needs to disambiguate and enrich entities.

Clean, small, structured output — one record per entity, ready for an LLM context or an agent tool response. Callable by Claude, ChatGPT, LangChain, CrewAI, LlamaIndex and any MCP client (every Apify actor is MCP-callable via mcp.apify.com).

🧠 The canonical grounding store. "Which Elon Musk? What is Apple's founder, industry, VIAF id? What type of thing is Berlin?" — the actor returns a single, sourced, machine-readable entity.

---

🤖 Why this is an AI-agent tool

Entity resolution is one of the most frequent needs of an agent: turn a fuzzy name into a stable ID plus facts, and link it across databases.

• ✅ Name → stable Q-ID — disambiguation an LLM can't do reliably alone
• ✅ Readable facts — type, occupation, dates, country, founders, industry (labels, not raw IDs)
• ✅ Cross-database IDs — VIAF, ISNI, ORCID, IMDb, Twitter/X, LinkedIn, GND, MusicBrainz, … for entity-linking
• ✅ MCP-ready — call it from any agent framework or MCP client

---

📋 What this actor does

Give it names (or Q-IDs) and it returns, for each:

• ✅ Q-ID, label and description
• ✅ Type — what it is (human, enterprise, city, …)
• ✅ Aliases — also-known-as
• ✅ Key facts — occupation, birth/death, citizenship, HQ, founders, industry, country, population, inception, …
• ✅ Cross-database identifiers — VIAF, ISNI, ORCID, IMDb, socials, GND, …
• ✅ Official website + Wikipedia + Wikidata URLs

---

🚀 Quick start

1. Enter one or more Names (e.g. Elon Musk, Apple Inc, Berlin).
2. (Optional) Add specific Q-IDs and a language.
3. Click Start and read the structured entities from Storage → Dataset.

---

⚙️ Input

Field	Type	Description
Names to resolve	array	Names to resolve, e.g. ["Elon Musk", "Apple Inc", "Berlin"].
Q-IDs	array	Resolve specific Wikidata Q-IDs directly, e.g. ["Q317521"].
Language	string	Label/description language (en, de, fr, es, tr, …).
Include key facts	boolean	Resolve facts to readable labels (type, occupation, founders, …).
Proxy	object	Optional — Wikidata is keyless with no anti-bot.

Example 1 — Resolve several names

{ "queries": ["Elon Musk", "Apple Inc", "Berlin"] }

Example 2 — Direct Q-IDs, German labels

{ "qids": ["Q317521", "Q312"], "language": "de" }

---

📦 Output

{
  "query": "Elon Musk",
  "qid": "Q317521",
  "label": "Elon Musk",
  "description": "American businessman (born 1971)",
  "type": "human",
  "aliases": "Elon Reeve Musk",
  "officialWebsite": null,
  "wikipediaUrl": "https://en.wikipedia.org/wiki/Elon_Musk",
  "wikidataUrl": "https://www.wikidata.org/wiki/Q317521",
  "facts": "{\"instanceOf\":\"human\",\"occupation\":[\"programmer\",\"engineer\"],\"birthDate\":\"1971-06-28\",\"citizenship\":[\"South Africa\",\"Canada\"]}",
  "externalIds": "{\"viaf\":\"306339060\",\"orcid\":\"0000-0001-8013-3548\",\"imdb\":\"nm1907769\",\"twitter\":\"elonmusk\",\"gnd\":\"1062481119\"}",
  "scrapedAt": "2026-07-04T00:00:00.000Z"
}

Output fields

Field	Description
query	The name/id that was resolved.
qid	Wikidata entity Q-ID.
label / description	Entity label and short description.
type	What it is (instance of).
aliases	Also-known-as.
officialWebsite	Official website.
wikipediaUrl / wikidataUrl	Source links.
facts	Key facts (type, occupation, dates, country, founders, industry, …) as JSON.
externalIds	Cross-database identifiers (VIAF, ISNI, ORCID, IMDb, socials, …) as JSON.

---

🔗 Cross-database identifiers

VIAF · ISNI · ORCID · IMDb · Twitter/X · Facebook · Instagram · YouTube · LinkedIn · TikTok · GND · Library of Congress · MusicBrainz · Spotify · Discogs · Quora · GRID · Ringgold — whichever are present on the entity.

---

🔌 AI & integrations

• MCP: every Apify actor is callable from mcp.apify.com — add this as a tool in Claude Desktop, VS Code or any MCP client.
• Frameworks: LangChain (ApifyActorsTool), LlamaIndex, CrewAI, Vercel AI SDK, n8n.
• API: run and fetch results with the Apify API or JS / Python clients.

---

❓ FAQ

Do I need an API key? No — Wikidata is keyless.

How is the best entity chosen? The top Wikidata search match for the name. For exact control, pass Q-IDs directly.

Are facts human-readable? Yes — referenced entities (occupation, country, founder, …) are resolved to labels, not raw Q-IDs.

Can an AI agent call this directly? Yes — it's designed as a tool-call source and is MCP-callable via Apify.

---

⚖️ Legal & responsible use

This actor uses the public Wikidata API. Wikidata content is available under CC0. Respect the API's rate limits and use a descriptive user agent (handled by the actor).

---

🛟 Support

Need an extra field or property? Open a ticket from the actor's Issues tab.

Happy resolving! 🧠