identify_entity_by_signals
Resolve an identity from partial signals like name, email, company, or domain. Returns a best match with confidence score and ranked candidates.
Instructions
Resolve an entity from a multi-signal bundle (name, email, company, domain, phone, and open-ended string props). Returns best_match with identity_score, resolution_band (high/medium/low/unresolved), ranked candidates, and matched_signals. Use when you have partial or combined identity information and want a single-call resolution with confidence scoring.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| signals | Yes | Bundle of identity signals. All fields are optional strings. The five well-known keys (name, email, company, domain, phone) receive their canonical weights; any additional keys are treated as open-ended string signals with weight 0.4. | |
| entity_type | No | Restrict resolution to this entity type. Takes precedence over entity_types. | |
| entity_types | No | Restrict resolution to these entity types. Merged with synonym-expanded types when combined with signals. | |
| max_candidates | No | Maximum candidates to return in the candidates array (best_match excluded). Default 5, max 20. | |
| include_observations | No | When true, attach recent observations to best_match and each candidate. | |
| user_id | No | Optional user_id override (scoped to callers with privilege to query on behalf of another user). |