Triple

T23366861
Position Surface form Disambiguated ID Type / Status
Subject Bob Daisley E593347 entity
Predicate associatedAct P37 FINISHED
Object Widowmaker NE NERFINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Widowmaker | Statement: [Bob Daisley, associatedAct, Widowmaker]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Widowmaker
Context triple: [Bob Daisley, associatedAct, Widowmaker]
  • A. Widowmaker
    Widowmaker is the ominous nickname given to the Martin B-26 Marauder, a World War II twin‑engine medium bomber notorious for its early reputation as difficult and dangerous to fly.
  • B. Widowmaker
    Widowmaker is a cold, blue-skinned Talon sniper assassin from the Overwatch universe, known for her lethal precision and emotionless demeanor.
  • C. Widowmaker chosen
    Widowmaker is a heavy metal band best known for featuring former Twisted Sister frontman Dee Snider and guitarist Al Pitrelli in the early 1990s.
  • D. Widow-Maker
    Widow-Maker is the famously wild and nearly unrideable horse of the American folk hero Pecos Bill in tall tales of the Old West.
  • E. The Widowmaker
    The Widowmaker is a 1990 British drama film about a junior doctor confronting systemic failures in the National Health Service, written by Jeremy Brock.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69e25d2593c88190bcdf4a716a94ccb2 completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f1a0ad621881908a909f236e6e9c90 completed April 29, 2026, 6:09 a.m.
Created at: April 17, 2026, 5:31 p.m.