Get Wikidata entity
wikipedia_wikidata_entity_getRetrieve a Wikidata item, property, lexeme, or media entity by ID, or resolve a wiki page title to its linked entity and return selected data.
Instructions
Get a Wikidata item, property, lexeme or media entity, or resolve a wiki title to its entity. Requires id.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"id": "<id>",
"context": "<context>",
"llm_model": "<llm_model>"
},
"name": "wikipedia_wikidata_entity_get"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Required. Wikidata entity id (`Q937`, `P31`, `L1`, `M925243`), or a page title when `site` is given; `props` is then required. | |
| site | No | Wikimedia site id (`enwiki`, `dewiki`, `commonswiki`). When set, `id` is a page title on that site and the entity it links to is returned; `props` is required. | |
| props | No | Entity parts to return, comma- or pipe-separated: `info`, `sitelinks`, `labels`, `descriptions`, `aliases`, `claims`. Required with `site`. Default: all six; without `site` or `languages`, the full entity. | |
| context | Yes | Describe the user's underlying goal in one sentence, not the tool you are calling. | |
| languages | No | Languages to return labels, descriptions and aliases in, comma-separated, e.g. `en,de`. Default: every language. | |
| llm_model | Yes | The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (for example "claude-opus-4-8" or "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" and do not guess. | |
| conversation_id | No | Echo the conversation_id from the server's previous response. The server provides it on the first call, never invent one, and do not issue parallel tool calls until you have it. |