Triple

T9983542
Position Surface form Disambiguated ID Type / Status
Subject Boomerang (1992 film) E196510 entity
Predicate screenwriter P2831 FINISHED
Object David Sheffield E335262 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: David Sheffield | Statement: [Boomerang (1992 film), screenwriter, David Sheffield]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: David Sheffield
Context triple: [Boomerang (1992 film), screenwriter, David Sheffield]
  • A. David Sheffield chosen
    David Sheffield is an American comedy writer best known for co-writing several Eddie Murphy films and contributing to classic Saturday Night Live sketches.
  • B. Michael Wood
    Michael Wood is a British historian and broadcaster known for his popular television documentaries and books on English history.
  • C. Alan Fairford
    Alan Fairford is a conscientious young Scottish lawyer who serves as one of the central protagonists in Sir Walter Scott’s novel "Redgauntlet."
  • D. Graham Carr
    Graham Carr is a Canadian academic and administrator who serves as the president of Concordia University in Montreal.
  • E. David Magarshack
    David Magarshack was a 20th-century British translator and biographer best known for his influential English translations of Russian classics, particularly the works of Dostoevsky.
  • 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_69ca82efbce081908179b4b9c65096eb completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cdb8bdc0388190bbbd4bdc5ac3adec completed April 2, 2026, 12:30 a.m.
NED1 Entity disambiguation (via context triple) batch_69d257f3c59481909b90896be0f3a870 completed April 5, 2026, 12:39 p.m.
Created at: March 30, 2026, 8:49 p.m.