Triple

T5433494
Position Surface form Disambiguated ID Type / Status
Subject What's Up, Doc? E121551 entity
Predicate starring P1507 FINISHED
Object Madeline Kahn E270772 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: Madeline Kahn | Statement: [What's Up, Doc?, starring, Madeline Kahn]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Madeline Kahn
Context triple: [What's Up, Doc?, starring, Madeline Kahn]
  • A. Madeline Kahn chosen
    Madeline Kahn was an American actress and comedian renowned for her distinctive voice and acclaimed performances in films such as "Blazing Saddles," "Young Frankenstein," and "Paper Moon."
  • B. Marion Grodin
    Marion Grodin is an American stand-up comedian, writer, and actress known for her sharp wit and for being the daughter of actor and comedian Charles Grodin.
  • C. Myrna Fahey
    Myrna Fahey was an American actress known for her film and television roles in the 1950s and 1960s, often appearing in comedies and dramas.
  • D. Mary Marquardt
    Mary Marquardt is an American former chef and illustrator best known as Harrison Ford’s first wife, to whom he was married from 1964 to 1979.
  • E. Arlene Francis
    Arlene Francis was an American actress, radio and television talk show host, and longtime panelist on the game show "What's My Line?"
  • 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_69bd463c65f0819082ee6483ab4b466a completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd91ae18cc8190aefe610f91b5382c completed March 20, 2026, 6:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf91f16c9c819088e7671ccf006189 completed March 22, 2026, 6:53 a.m.
Created at: March 20, 2026, 2:06 p.m.