Triple

T13481129
Position Surface form Disambiguated ID Type / Status
Subject Donnie Darko E318373 entity
Predicate writer P1360 FINISHED
Object Richard Kelly E1043042 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: Richard Kelly | Statement: [Donnie Darko, writer, Richard Kelly]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Richard Kelly
Context triple: [Donnie Darko, writer, Richard Kelly]
  • A. Richard Kelly chosen
    Richard Kelly is an American filmmaker best known for writing and directing the cult psychological sci-fi film "Donnie Darko."
  • B. José Padilha
    José Padilha is a Brazilian filmmaker best known internationally for directing the "Elite Squad" films and the 2014 "RoboCop" remake, as well as producing and directing episodes of the crime drama series "Narcos."
  • C. Alan Burgess
    Alan Burgess was a British author and screenwriter best known for writing the book that inspired the film "The Inn of the Sixth Happiness."
  • D. Paul Haggis
    Paul Haggis is a Canadian screenwriter, producer, and director best known for writing and directing the Academy Award–winning film "Crash" and co-writing "Million Dollar Baby."
  • E. John Dahl
    John Dahl is an American film and television director best known for his stylish neo-noir thrillers such as "Red Rock West" and "The Last Seduction."
  • 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_69d806b6bfec819089222715b2e86c8e completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69dbaf36c6b08190ba99400600e0b662 completed April 12, 2026, 2:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69f75481b6f48190b6cd6cef3e8dee20 completed May 3, 2026, 1:58 p.m.
Created at: April 9, 2026, 9:42 p.m.