Triple

T19754806
Position Surface form Disambiguated ID Type / Status
Subject Mervyn Peake E474475 entity
Predicate name P16 FINISHED
Object Mervyn Peake 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: Mervyn Peake | Statement: [Mervyn Peake, name, Mervyn Peake]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mervyn Peake
Context triple: [Mervyn Peake, name, Mervyn Peake]
  • A. Mervyn Peake chosen
    Mervyn Peake was a British writer and illustrator best known for his richly imaginative and gothic Gormenghast fantasy series.
  • B. Charles Williams
    Charles Williams was an American author best known for his hardboiled crime and suspense novels, including the maritime thriller "Dead Calm."
  • C. E. R. Eddison
    E. R. Eddison was a British author best known for his influential early 20th-century high fantasy novels, particularly "The Worm Ouroboros" and the Zimiamvian Trilogy.
  • D. Richard Llewellyn
    Richard Llewellyn was a Welsh novelist best known for his 1939 work "How Green Was My Valley," a classic depiction of life in a South Wales mining community.
  • E. Nigel Balchin
    Nigel Balchin was a British novelist and screenwriter known for his psychologically insightful wartime and postwar fiction, including the novel that inspired the film "Separate Lies."
  • 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_69d8e51940a0819087bd2996f98da668 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6529dada081909c5b4d65247c6032 completed April 20, 2026, 4:21 p.m.
Created at: April 10, 2026, 1:48 p.m.