Triple

T10477768
Position Surface form Disambiguated ID Type / Status
Subject Blade (1998 film) E247089 entity
Predicate producer P490 FINISHED
Object Robert Engelman E530522 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: Robert Engelman | Statement: [Blade (1998 film), producer, Robert Engelman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Robert Engelman
Context triple: [Blade (1998 film), producer, Robert Engelman]
  • A. Robert Engelman chosen
    Robert Engelman is a film producer known for his work on major Hollywood genre films, including action, science fiction, and fantasy projects.
  • B. Bob Engelman
    Bob Engelman is a film producer best known for working on major Hollywood movies, including the hit comedy "The Mask."
  • C. Steven Fierberg
    Steven Fierberg is an American cinematographer known for his work on feature films and television series, including the romantic drama "Love & Other Drugs."
  • D. Richard Sokolove
    Richard Sokolove is a screenwriter best known for his work on the historical drama film "Anne of the Thousand Days."
  • E. Jeffrey Auerbach
    Jeffrey Auerbach is a film producer best known for his work on the stop-motion animated feature "Corpse Bride."
  • 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_69d381c16c248190a2fe5b471e584e9c completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d509596a088190895199648ccf91a4 completed April 7, 2026, 1:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69e5d2d717888190b7e455d006d01033 completed April 20, 2026, 7:16 a.m.
Created at: April 6, 2026, 12:21 p.m.