Triple

T8319674
Position Surface form Disambiguated ID Type / Status
Subject Horns (film) E194797 entity
Predicate character P662 FINISHED
Object Ignatius Perrish E725778 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: Ignatius Perrish | Statement: [Horns (film), character, Ignatius Perrish]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ignatius Perrish
Context triple: [Horns (film), character, Ignatius Perrish]
  • A. Ignatius Perrish chosen
    Ignatius Perrish is the troubled protagonist of Joe Hill's dark fantasy novel "Horns," who mysteriously grows devilish horns that compel people to confess their darkest secrets.
  • B. Ignatius Sargent
    Ignatius Sargent was a prominent 19th-century American businessman and financier known for his influential role in New England’s early industrial and railroad development.
  • C. Samuel Dracott
    Samuel Dracott is an individual whose name appears in records with the variant spelling "Samuel Dracutt."
  • D. Christian Van Dyke
    Christian Van Dyke is one of the children of legendary American actor and entertainer Dick Van Dyke.
  • E. Abner Underhill
    Abner Underhill is a historical figure known primarily for bearing the surname Underhill, which is associated with early American colonial and genealogical records.
  • 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_69ca82e7a8a88190a32bb5cc0feb012d completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb7f6686a0819094abc2bfd2e500a5 completed March 31, 2026, 8:01 a.m.
NED1 Entity disambiguation (via context triple) batch_69ce0278b9a88190a57a6b1b31c39ee8 completed April 2, 2026, 5:45 a.m.
Created at: March 30, 2026, 5:55 p.m.