Triple

T16391463
Position Surface form Disambiguated ID Type / Status
Subject William Herbert Hunt E398061 entity
Predicate hasRelative P367 FINISHED
Object Hassie Hunt E1207642 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: Hassie Hunt | Statement: [William Herbert Hunt, hasRelative, Hassie Hunt]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hassie Hunt
Context triple: [William Herbert Hunt, hasRelative, Hassie Hunt]
  • A. Hassie Hunt chosen
    Hassie Hunt was a member of the prominent Hunt family, known primarily as one of the heirs to Texas oil magnate H. L. Hunt’s fortune.
  • B. Laura Hunt
    Laura Hunt is the enigmatic advertising executive at the center of the classic 1944 film noir "Laura," whose apparent murder and idealized image drive the film’s mystery and romantic obsession.
  • C. Jodie Harrison
    Jodie Harrison is an Australian Labor Party politician who serves as a minister in the New South Wales government.
  • D. Hannah Jackson
    Hannah Jackson was the wife of American industrialist Francis Cabot Lowell, associated with the early development of the U.S. textile industry.
  • E. Jessica Reedy
    Jessica Reedy is an American gospel singer and songwriter known for her soulful vocals and for gaining national attention as a finalist on BET’s “Sunday Best.”
  • 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_69d87f2880b48190ae1a9673a3bbef80 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e326425c8081908cacffcfa8c7386b completed April 18, 2026, 6:35 a.m.
NED1 Entity disambiguation (via context triple) batch_6a004579d9a88190b353952c5c301e9f completed May 10, 2026, 8:44 a.m.
Created at: April 10, 2026, 5:08 a.m.