Find related entities
find_relatedSubjects, people, places and projects connected through shared records. Per-corpus counts deduplicate each record; subject/person seeds also include publications, subject/place/person seeds Cluster Chronicles works. Returns ambiguity and cited samples.
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": {
"entity_type": "<entity_type>",
"value": "<value>"
},
"name": "find_related"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Cap on each related_* list, default 20, max 50; sample lists show at most 10 | |
| value | Yes | The entity to pivot on. subject: substring of a heading ('Islam'). location: any level of the city→country hierarchy ('Nigeria' includes Lagos items). person: a name in either order, accent-insensitive ('Beier, Ulli'). project: an Omeka id ('37700'), a legacy key, or the project name or whole words of it. research_item: an item id ('27733' or 'research_item:27733'), not a text query. record: an omeka_id or typed id ('publication:29919') | |
| entity_type | Yes | What the value denotes. Tags are merged into subjects. research_item: the id of an ILAM African Music article, related by full text. record: any embedded record, related by meaning |