Triple

T14397560
Position Surface form Disambiguated ID Type / Status
Subject Three Men and a Little Lady E356988 entity
Predicate mainCharacter P1183 FINISHED
Object Mary Bennington E1096634 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: Mary Bennington | Statement: [Three Men and a Little Lady, mainCharacter, Mary Bennington]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mary Bennington
Context triple: [Three Men and a Little Lady, mainCharacter, Mary Bennington]
  • A. Mary Bennington chosen
    Mary Bennington is the infant around whom the comedic and emotional events of the film "Three Men and a Baby" revolve.
  • B. Kerry King
    Kerry King is an American guitarist best known as the co-founder and lead guitarist of the influential thrash metal band Slayer.
  • C. Emily Young
    Emily Young is a British film director and screenwriter known for her work on independent and literary adaptation films.
  • D. Joanne Carlisle
    Joanne Carlisle is the mother of American singer Belinda Carlisle, the lead vocalist of the Go-Go's.
  • E. D’arcy Wretzky
    D’arcy Wretzky is an American musician best known as the original bassist of the alternative rock band The Smashing Pumpkins.
  • 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_69d827927c988190ad98bb0360981783 completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de90826f908190b3969af9b7cf922f completed April 14, 2026, 7:07 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd5bc424f88190ab3a1c1aec61cb40 completed May 8, 2026, 3:43 a.m.
Created at: April 10, 2026, 1:17 a.m.