Triple

T20728824
Position Surface form Disambiguated ID Type / Status
Subject William Gaxton E509511 entity
Predicate coStar P43875 FINISHED
Object Ethel Merman 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: Ethel Merman | Statement: [William Gaxton, coStar, Ethel Merman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ethel Merman
Context triple: [William Gaxton, coStar, Ethel Merman]
  • A. Ethel Merman chosen
    Ethel Merman was a powerhouse American stage and film actress and singer, famed for her brassy voice and iconic performances in classic Broadway musicals such as "Gypsy" and "Annie Get Your Gun."
  • B. Gwen Verdon
    Gwen Verdon was an acclaimed American actress and dancer best known for her Tony Award–winning performances in Broadway musicals such as "Damn Yankees" and "Chicago."
  • C. Olivia Hamilton
    Olivia Hamilton is an American actress and producer known for her work in films such as "La La Land" and "First Man."
  • D. Gladys Lehman
    Gladys Lehman was an American screenwriter active during Hollywood’s classic era, known for her work on several notable studio films.
  • E. Helen Merrill
    Helen Merrill is an American jazz vocalist renowned for her cool, introspective style and influential recordings with leading jazz musicians of the 1950s.
  • 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_69e0b4c4cc648190b45fda6e2b20af56 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c1eb5d44819082d9fa410e676d91 completed April 21, 2026, 12:16 a.m.
Created at: April 16, 2026, 12:30 p.m.