Triple

T21250879
Position Surface form Disambiguated ID Type / Status
Subject Blazing Saddles E523740 entity
Predicate coWriter P2389 FINISHED
Object Andrew Bergman 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: Andrew Bergman | Statement: [Blazing Saddles, coWriter, Andrew Bergman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Andrew Bergman
Context triple: [Blazing Saddles, coWriter, Andrew Bergman]
  • A. Andrew Bergman chosen
    Andrew Bergman is an American screenwriter, novelist, and film director known for his work on comedies such as "Blazing Saddles," "The In-Laws," and "Honeymoon in Vegas."
  • B. William Bergman
    William Bergman is an entrepreneur best known as the founder of the lip care and skincare brand Blistex.
  • C. John Stahl
    John Stahl was a Scottish actor known for his work in theatre, television, and film, including roles in productions such as the National Theatre's "Frankenstein" and the TV series "Game of Thrones."
  • D. Hans Alfredson
    Hans Alfredson was a renowned Swedish comedian, actor, writer, and director, best known as one half of the influential comedy duo Hasse & Tage.
  • E. Martin Bergman
    Martin Bergman is a British screenwriter and producer best known for co-writing the 1992 ensemble comedy-drama film "Peter’s Friends."
  • 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_69e0b5146c108190adc9adb73e90abff completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e7359da6e08190a96c471463c2388d completed April 21, 2026, 8:30 a.m.
Created at: April 16, 2026, 3:56 p.m.