Triple

T22838433
Position Surface form Disambiguated ID Type / Status
Subject Last Orders (novel) E566009 entity
Predicate author P4 FINISHED
Object Graham Swift 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: Graham Swift | Statement: [Last Orders (novel), author, Graham Swift]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Graham Swift
Context triple: [Last Orders (novel), author, Graham Swift]
  • A. Graham Swift chosen
    Graham Swift is a British novelist known for his psychologically rich, intricately structured works such as "Waterland" and "Last Orders," which explore memory, history, and personal identity.
  • B. David Lodge
    David Lodge was a British character actor known for his numerous supporting roles in mid-20th-century film and television comedies.
  • C. Jonathan Coe
    Jonathan Coe is a British novelist and satirist best known for works such as "What a Carve Up!" and "The Rotters' Club," which often blend political commentary with dark humor.
  • D. Julian Barnes
    Julian Barnes is a distinguished contemporary English novelist and essayist known for his inventive narratives and exploration of memory, history, and identity.
  • E. Ali Smith
    Ali Smith is a Scottish author acclaimed for her inventive, genre-blurring novels and short stories, including the seasonal quartet that begins with "Autumn."
  • 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_69e245869e188190a196584f36e682da completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17e8244dc819089c0a7525fb512ab completed April 29, 2026, 3:44 a.m.
Created at: April 17, 2026, 3:35 p.m.