Triple

T6945691
Position Surface form Disambiguated ID Type / Status
Subject Constantine (2005 film) E160792 entity
Predicate producer P490 FINISHED
Object Erwin Stoff E350670 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: Erwin Stoff | Statement: [Constantine (2005 film), producer, Erwin Stoff]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Erwin Stoff
Context triple: [Constantine (2005 film), producer, Erwin Stoff]
  • A. Erwin Stoff chosen
    Erwin Stoff is a Hollywood film producer and talent manager known for overseeing major studio projects and guiding the careers of high-profile actors.
  • B. Erwin Bälz
    Erwin Bälz was a German internist and physiologist renowned for his pioneering contributions to modern medicine in Japan during the Meiji era.
  • C. Carl Schuhmann
    Carl Schuhmann was a German athlete renowned for winning multiple gold medals in gymnastics and wrestling at the inaugural modern Olympic Games in 1896.
  • D. Erwin Kurtz
    Erwin Kurtz is a person notable enough to be recognized as a significant bearer of the surname Kurtz.
  • E. Charles Bergstresser
    Charles Bergstresser was an American journalist and financier best known as one of the co-founders of The Wall Street Journal.
  • 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_69c68850419081909fb426b8f5a304c7 completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6da8a65c48190b6862fc60f6c7f7a completed March 27, 2026, 7:29 p.m.
NED1 Entity disambiguation (via context triple) batch_69c968c9a1a48190b6ea5bb08ff745af completed March 29, 2026, 6 p.m.
Created at: March 27, 2026, 2:28 p.m.