Triple

T20884811
Position Surface form Disambiguated ID Type / Status
Subject Callaghan family E514248 entity
Predicate hasNotableMember P304 FINISHED
Object Hilary Callaghan 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: Hilary Callaghan | Statement: [Callaghan family, hasNotableMember, Hilary Callaghan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hilary Callaghan
Context triple: [Callaghan family, hasNotableMember, Hilary Callaghan]
  • A. Hilary Callaghan chosen
    Hilary Callaghan is a British mathematician known for her work in probability theory and as the daughter of former UK Prime Minister James Callaghan.
  • B. Catherine McGinty
    Catherine McGinty is a fictional character from the 1940 political satire film "The Great McGinty," directed by Preston Sturges.
  • C. Katharine Cullen
    Katharine Cullen is an Australian actress known for her work in film, television, and theatre, and as the daughter of actor Max Cullen.
  • D. Katie Higgins
    Katie Higgins is the central protagonist of the 1953 MGM musical film "Dangerous When Wet," portrayed as a wholesome, athletic farm girl who trains to swim the English Channel.
  • E. Catherine Leahy
    Catherine Leahy is a notable individual who shares the surname Leahy, recognized enough to be specifically cited as a bearer of the name.
  • 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_69e0b4f733f081908a401c0b7beb0b9f completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c67bd32c819097301e330e358c49 completed April 21, 2026, 12:36 a.m.
Created at: April 16, 2026, 12:46 p.m.