Triple

T3568156
Position Surface form Disambiguated ID Type / Status
Subject Graham E75501 entity
Predicate hasNotableBearer P458 FINISHED
Object Graham Greene E159431 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: Graham Greene | Statement: [Graham, hasNotableBearer, Graham Greene]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Graham Greene
Context triple: [Graham, hasNotableBearer, Graham Greene]
  • A. Graham Greene chosen
    Graham Greene was a prominent 20th-century British novelist and playwright known for his psychologically complex thrillers and explorations of moral and political ambiguity.
  • B. Edgar Box
    Edgar Box is the crime-fiction pseudonym under which American writer Gore Vidal published a series of mystery novels in the 1950s.
  • C. Anthony Powell
    Anthony Powell was an English novelist best known for his twelve-volume series "A Dance to the Music of Time," a landmark of 20th-century British literature.
  • D. John Fowles
    John Fowles was an English novelist best known for works such as "The Collector," "The Magus," and "The French Lieutenant's Woman," which blend psychological depth with metafictional and philosophical themes.
  • E. L. P. Hartley
    L. P. Hartley was a British novelist best known for his 1953 novel "The Go-Between," a classic exploration of memory, class, and lost innocence.
  • 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_69ad85d512708190829c8b2d3a2ccfb8 completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc0ab51d881908f004fae47ab09d9 completed March 8, 2026, 6:32 p.m.
NED1 Entity disambiguation (via context triple) batch_69b3bbb01d108190bd098c86b0180b78 completed March 13, 2026, 7:24 a.m.
Created at: March 8, 2026, 3:21 p.m.