Triple

T10813361
Position Surface form Disambiguated ID Type / Status
Subject The 3 Worlds of Gulliver E255159 entity
Predicate cinematographyBy P1953 FINISHED
Object Wilkie Cooper E801136 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: Wilkie Cooper | Statement: [The 3 Worlds of Gulliver, cinematographyBy, Wilkie Cooper]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Wilkie Cooper
Context triple: [The 3 Worlds of Gulliver, cinematographyBy, Wilkie Cooper]
  • A. Wilkie Cooper chosen
    Wilkie Cooper was a British cinematographer known for his work on mid-20th-century films, particularly in the thriller and fantasy genres.
  • B. Henry MacRae
    Henry MacRae was an early 20th-century American film producer and director known for his work on serials and genre films at Universal Pictures.
  • C. Hamish MacCunn
    Hamish MacCunn was a Scottish late-Romantic composer and conductor best known for his orchestral and choral works inspired by Scottish landscapes and folklore.
  • D. Henry Sharp
    Henry Sharp was an American cinematographer known for his work on numerous early 20th-century films, including the adventure drama "The Iron Mask."
  • E. Joseph Meredith
    Joseph Meredith is known as the son of James Meredith, the civil rights figure who integrated the University of Mississippi.
  • 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_69d6aa61c15c8190a1839550c56e75e1 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d733eba9b48190b4dbe7fe5d8be0a4 completed April 9, 2026, 5:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69deb0ea2b6481909dfd94fe0c3c4499 completed April 14, 2026, 9:26 p.m.
Created at: April 8, 2026, 9:18 p.m.