Triple

T18711657
Position Surface form Disambiguated ID Type / Status
Subject Kevin Flynn E457527 entity
Predicate ally P4662 FINISHED
Object Alan Bradley 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: Alan Bradley | Statement: [Kevin Flynn, ally, Alan Bradley]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Alan Bradley
Context triple: [Kevin Flynn, ally, Alan Bradley]
  • A. Alan Bradley chosen
    Alan Bradley is a key character in the Tron franchise, known as the brilliant programmer who created the security program Tron and serves as a close ally of Kevin Flynn.
  • B. Val McDermid
    Val McDermid is a Scottish crime writer renowned for her psychological thrillers and influential contributions to contemporary crime fiction.
  • C. Christopher Fowler
    Christopher Fowler was a British author best known for his Bryant & May mystery novels and his work in horror and dark fantasy fiction.
  • D. Susan Hill
    Susan Hill is a British author best known for her ghost stories and novels, including the modern classic "The Woman in Black."
  • E. Martha Grimes
    Martha Grimes is an American author best known for her long-running series of British detective novels featuring Scotland Yard inspector Richard Jury.
  • 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_69d8d392aad081909fe31aa03e6e97d1 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e5671c53988190bfc132c853cebd02 completed April 19, 2026, 11:37 p.m.
Created at: April 10, 2026, 11:50 a.m.