Triple

T17680084
Position Surface form Disambiguated ID Type / Status
Subject Ink (2017) E440745 entity
Predicate writer P1360 FINISHED
Object James Graham 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: James Graham | Statement: [Ink (2017), writer, James Graham]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: James Graham
Context triple: [Ink (2017), writer, James Graham]
  • A. James Graham
    James Graham is a pseudonym used by British thriller novelist Jack Higgins, famed for his bestselling espionage and war-themed novels.
  • B. James Graham
    James Graham was a 17th-century Scottish nobleman, soldier, and poet best known for leading Royalist forces during the Wars of the Three Kingdoms.
  • C. James Graham
    James Graham is the father of American actress Heather Graham.
  • D. James Graham
    James Graham is an internet entrepreneur best known for founding and developing the online quiz platform Quiz.
  • E. James Graham chosen
    James Graham is a British playwright and screenwriter known for his politically charged dramas and television scripts, including the film "Brexit: The Uncivil War."
  • 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_69d8b9e940b081908b862bb0e6e89b0d completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e4704357b8819087e3a93e9eefd858 completed April 19, 2026, 6:03 a.m.
Created at: April 10, 2026, 10:01 a.m.