Triple

T22750693
Position Surface form Disambiguated ID Type / Status
Subject Gerald Sheldon Herman E562686 entity
Predicate notableWork P4 FINISHED
Object Mame 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: Mame | Statement: [Gerald Sheldon Herman, notableWork, Mame]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mame
Context triple: [Gerald Sheldon Herman, notableWork, Mame]
  • A. Mame chosen
    Mame is the flamboyant, free-spirited title character of the stage musical "Mame," known for her larger-than-life personality and unconventional approach to life and family.
  • B. Mame (1974 film)
    Mame (1974 film) is a 1974 musical comedy movie adaptation of the Broadway musical, starring Lucille Ball as the eccentric socialite Auntie Mame.
  • C. You Can't Take It with You
    You Can't Take It with You is a Pulitzer Prize–winning 1936 comedic play by Moss Hart and George S. Kaufman about an eccentric family whose free-spirited lifestyle clashes with conventional society.
  • D. Can’t Take It With You
    "Can’t Take It With You" is a country song by Eric Church featured on his debut album "Sinners Like Me."
  • E. My Mammy
    "My Mammy" is a popular early 20th-century American song closely associated with Al Jolson and classic vaudeville and film performances.
  • 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_69e24551ec7881909a9c924dbea155f6 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f179b8e9408190b251700d3386a1b9 completed April 29, 2026, 3:23 a.m.
Created at: April 17, 2026, 3:24 p.m.