Triple

T12660830
Position Surface form Disambiguated ID Type / Status
Subject Lloyd Bacon E302417 entity
Predicate spouse P13 FINISHED
Object Hazel Bennet E302417 NE FINISHED

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: Hazel Bennet | Statement: [Lloyd Bacon, spouse, Hazel Bennet]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hazel Bennet
Context triple: [Lloyd Bacon, spouse, Hazel Bennet]
  • A. Hazel Bennet chosen
    Hazel Bennet was the wife of American film director and actor Lloyd Bacon, associated with Hollywood’s early studio era.
  • B. Hazel Bliss
    Hazel Bliss was the wife of American aviator and businessman Albert Bond Lambert, associated with early 20th-century St. Louis society.
  • C. Hazel Langford
    Hazel Langford is the wife of British science fiction author and critic David Langford.
  • D. Hazel Jenkins
    Hazel Jenkins is a South African politician who served as Premier of the Northern Cape province.
  • E. Hazel Dorothy Scott
    Hazel Dorothy Scott was a Trinidadian-American jazz and classical pianist, singer, and civil rights activist renowned for her virtuosic performances and trailblazing presence in film and television.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d7bded71a88190bb76e2413af9ea66 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d9617b07ec8190b714f04ae6654060 completed April 10, 2026, 8:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69f739688734819092b14bd3edacd4ef completed May 3, 2026, 12:02 p.m.
Created at: April 9, 2026, 5:19 p.m.