Triple

T18875613
Position Surface form Disambiguated ID Type / Status
Subject The Revenge of Frankenstein E461675 entity
Predicate screenwriter P2831 FINISHED
Object Jimmy Sangster 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: Jimmy Sangster | Statement: [The Revenge of Frankenstein, screenwriter, Jimmy Sangster]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jimmy Sangster
Context triple: [The Revenge of Frankenstein, screenwriter, Jimmy Sangster]
  • A. Jimmy Sangster chosen
    Jimmy Sangster was a British screenwriter and director best known for his influential work on Hammer Films’ classic horror movies in the 1950s and 1960s.
  • B. John Gilling
    John Gilling was a British film director and screenwriter best known for his work on mid-20th-century horror and thriller films, particularly for Hammer Film Productions.
  • C. John Paddy Carstairs
    John Paddy Carstairs was a British film director and screenwriter best known for his work on mid-20th-century comedies, including several films starring Norman Wisdom.
  • D. Lee Thompson
    Lee Thompson is a British saxophonist and songwriter best known as a founding member of the ska band Madness.
  • E. Richard Arlen
    Richard Arlen was an American film actor best known for his roles in early Hollywood, particularly in silent and early sound-era adventure and war films.
  • 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_69d8dcfc3430819095ee6fc0eb4c06a5 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5c3ce07788190a179705eb1b6c824 completed April 20, 2026, 6:12 a.m.
Created at: April 10, 2026, 11:57 a.m.