Triple

T9845678
Position Surface form Disambiguated ID Type / Status
Subject 13 Ghosts E239336 entity
Predicate producer P490 FINISHED
Object William Castle E571475 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: William Castle | Statement: [13 Ghosts, producer, William Castle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: William Castle
Context triple: [13 Ghosts, producer, William Castle]
  • A. William Castle chosen
    William Castle was an American film director and producer best known for his low-budget horror movies and inventive, gimmick-driven promotional stunts in the 1950s and 1960s.
  • B. Samuel Z. Arkoff
    Samuel Z. Arkoff was an influential American film producer and co-founder of American International Pictures, known for pioneering low-budget genre and exploitation films in the mid-20th century.
  • C. Ivan Tors
    Ivan Tors was a Hungarian-American film and television producer best known for creating and producing animal- and nature-focused adventure series such as Flipper, Daktari, and Gentle Ben.
  • D. Russ Meyer
    Russ Meyer was an American filmmaker best known for his low-budget, sexploitation cult films featuring satirical humor and voluptuous female leads.
  • E. Clarence Kolster
    Clarence Kolster was an American film editor best known for his work on classic Hollywood films in the early 20th century.
  • 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_69ca84e3f0c48190ada72a65ebd50efd completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cdb35ff7848190a8a717773d8654b9 completed April 2, 2026, 12:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69d1e42edd98819092d07139890d83e4 completed April 5, 2026, 4:25 a.m.
Created at: March 30, 2026, 8:34 p.m.