Triple

T14904765
Position Surface form Disambiguated ID Type / Status
Subject John Hurt E360099 entity
Predicate spouse P13 FINISHED
Object Donna Peacock 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: Donna Peacock | Statement: [John Hurt, spouse, Donna Peacock]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Donna Peacock
Context triple: [John Hurt, spouse, Donna Peacock]
  • A. Donna Peacock chosen
    Donna Peacock is a British production assistant best known for being the second wife of acclaimed actor John Hurt.
  • B. Donna Richards
    Donna Richards is known as the wife of Canadian-American journalist and television news anchor Robert MacNeil.
  • C. Donna Tubbs
    Donna Tubbs is a central character in the animated sitcom universe of Family Guy and The Cleveland Show, known as Cleveland Brown's strong-willed, caring, and often no-nonsense wife.
  • D. Donna Norris
    Donna Norris is best known as the mother of Amber Hagerman, whose 1996 abduction and murder led to the creation of the AMBER Alert child abduction emergency response system.
  • E. Donna Clark
    Donna Clark is a central character in the television series "Halt and Catch Fire," portrayed as a brilliant engineer and businesswoman navigating the evolving personal computer and tech startup landscape of the 1980s and 1990s.
  • 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_69d827980cbc8190a0c569ae3940a1d9 completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69ded60cd5588190b1efecc2b220da69 completed April 15, 2026, 12:04 a.m.
Created at: April 10, 2026, 2:12 a.m.