Version: latest

`agrag.ingestion.stats.resolution.ResolutionStats`

Bases: BaseModel

Resolution-stage results.

Attributes:

exact_match_hits (int) – Mentions that matched an already-persisted entity via the global exact-match tier.
in_batch_groups (int) – Groups of two or more mentions from this batch that the fuzzy, embedding, or LLM tier formed. Unmatched mentions are not groups.
ambiguous_count (int) – LLM answers that were uncertain, missing, or malformed. These pairs are never merged.
failed_llm_requests (int) – LLM verification requests that raised. Their pairs stay undecided and are not merged.
cap_truncated_pairs (int) – Ambiguous pairs over the per-label max_llm_pairs cap. They never reached the LLM.
llm_unavailable_pairs (int) – Ambiguous pairs skipped because no LLM settings were found.

`ambiguous_count`

ambiguous_count: int = 0

cap_truncated_pairs: int = 0

exact_match_hits: int = 0

failed_llm_requests: int = 0

in_batch_groups: int = 0

llm_unavailable_pairs: int = 0