Triple

T15855823
Position Surface form Disambiguated ID Type / Status
Subject Martha Hunt E384452 entity
Predicate name P16 FINISHED
Object Martha Hunt 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: Martha Hunt | Statement: [Martha Hunt, name, Martha Hunt]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Martha Hunt
Context triple: [Martha Hunt, name, Martha Hunt]
  • A. Martha Hunt chosen
    Martha Hunt is an American fashion model best known for her work with Victoria’s Secret, including serving as a Victoria’s Secret Angel.
  • B. Martha Hudson
    Martha Hudson is an American sprinter who was one of the top female track athletes of her era, notably competing internationally under coach Ed Temple at Tennessee State University.
  • C. Martha Williamson
    Martha Williamson is an American television producer and writer best known for developing and leading the hit inspirational drama series "Touched by an Angel."
  • D. Martha Thompson
    Martha Thompson was the wife of Confederate Lieutenant General John C. Pemberton, noted for his role in the American Civil War.
  • E. Martha Dix
    Martha Dix was the wife and frequent model of German painter Otto Dix, known from many of his portraits and family scenes.
  • 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_69d86da422088190aac39e32e6c68429 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e14cb08bd081908af2120eb2925441 completed April 16, 2026, 8:55 p.m.
Created at: April 10, 2026, 4:50 a.m.