Triple

T22032513
Position Surface form Disambiguated ID Type / Status
Subject Red Dragon E544120 entity
Predicate mainCharacter P1183 FINISHED
Object Will 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: Will Graham | Statement: [Red Dragon, mainCharacter, Will Graham]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Will Graham
Context triple: [Red Dragon, mainCharacter, Will Graham]
  • A. Will Graham chosen
    Will Graham is a gifted but psychologically fragile FBI profiler known for his uncanny ability to empathize with and understand the minds of serial killers in Thomas Harris's Hannibal Lecter series.
  • B. John Graham
    John Graham is an Australian Labor Party politician who serves as a senior minister in the New South Wales government under Premier Chris Minns.
  • C. John Graham
    John Graham was a British colonial military officer after whom the South African town of Grahamstown (now Makhanda) was named.
  • D. Doug Graham
    Doug Graham is a New Zealand politician and lawyer who served as a senior National Party cabinet minister, notably overseeing major legal and Treaty of Waitangi settlement reforms.
  • E. Ian Graham
    Ian Graham was a prominent British Mayanist archaeologist and epigrapher known for his extensive documentation and study of ancient Maya sites and inscriptions.
  • 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_69e11e2f98c8819083e11eab90942a78 completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f127ee84848190a22c24bf14498520 completed April 28, 2026, 9:34 p.m.
Created at: April 16, 2026, 8:24 p.m.