Triple

T21664971
Position Surface form Disambiguated ID Type / Status
Subject Stephen Fleming E534689 entity
Predicate spouse P13 FINISHED
Object Ingrid Fleming 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: Ingrid Fleming | Statement: [Stephen Fleming, spouse, Ingrid Fleming]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ingrid Fleming
Context triple: [Stephen Fleming, spouse, Ingrid Fleming]
  • A. Ingrid Fleming
    Ingrid Fleming is a character in the 1992 British romantic drama film "Damage," which explores a destructive affair and its impact on a prominent political family.
  • B. Ingrid Fleming chosen
    Ingrid Fleming is a relative of former New Zealand cricket captain Stephen Fleming, known primarily in relation to his family background.
  • C. Louise McIntyre
    Louise McIntyre is the wife of Trapper John McIntyre, a central character from the M*A*S*H franchise.
  • D. Alexandra MacInnes
    Alexandra MacInnes is the mother of Canadian actress and singer Jacqueline MacInnes Wood.
  • E. Ruby Pratt
    Ruby Pratt is a central character in the British period drama "Lark Rise to Candleford," known for her role in the close-knit rural community depicted in the series.
  • 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_69e0c467e1f48190af2650b19175abc4 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ef6c0b26c8819092c13e59dcc3c25c completed April 27, 2026, 2 p.m.
Created at: April 16, 2026, 6:36 p.m.