Triple

T20808121
Position Surface form Disambiguated ID Type / Status
Subject The Women E512218 entity
Predicate hasCharacter P2308 FINISHED
Object Mary Haines 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: Mary Haines | Statement: [The Women, hasCharacter, Mary Haines]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mary Haines
Context triple: [The Women, hasCharacter, Mary Haines]
  • A. Mary Haines chosen
    Mary Haines is the gracious, upper-class New York wife and mother whose marital troubles and friendships drive the plot of the 1939 film "The Women."
  • B. Mary Barstow
    Mary Barstow was the second wife of American illustrator Norman Rockwell and the mother of his three sons.
  • C. Mary Lee Hartford
    Mary Lee Hartford was the second wife of American actor and producer Douglas Fairbanks Jr., known primarily for her marriage into the prominent Fairbanks family.
  • D. Marguerite Hensley
    Marguerite Hensley is best known as the mother of Cindy McCain, the American businesswoman and philanthropist who was married to U.S. Senator John McCain.
  • E. Elizabeth Hanks
    Elizabeth Hanks is an American actress and writer, known for her supporting roles in films like "Forrest Gump" and for being the daughter of actor Tom Hanks.
  • 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_69e0b4cc69f481908e98751e697b9df4 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c2d0a2a081908fb0e3d890e87aaf completed April 21, 2026, 12:20 a.m.
Created at: April 16, 2026, 12:40 p.m.