Triple

T20681642
Position Surface form Disambiguated ID Type / Status
Subject Ngaio Marsh E508305 entity
Predicate notableWork P4 FINISHED
Object Died in the Wool 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: Died in the Wool | Statement: [Ngaio Marsh, notableWork, Died in the Wool]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Died in the Wool
Context triple: [Ngaio Marsh, notableWork, Died in the Wool]
  • A. Died in the Wool chosen
    Died in the Wool is a detective novel by Ngaio Marsh featuring Inspector Roderick Alleyn, set on a remote New Zealand sheep station.
  • B. Besses o’ th’ Barn
    Besses o’ th’ Barn is a suburban area in Whitefield, Greater Manchester, England, historically known as a small settlement that grew around a coaching inn on the main road between Manchester and Bury.
  • C. Waking Ned Devine
    Waking Ned Devine is a 1998 Irish comedy film about a small village conspiring to claim a deceased man's winning lottery ticket.
  • D. The Green Green Grass
    The Green Green Grass is a British sitcom and spin-off of Only Fools and Horses that follows Boycie and his family as they relocate from Peckham to the countryside.
  • E. Drop the Dead Donkey
    Drop the Dead Donkey is a British satirical sitcom set in a chaotic TV newsroom, known for its topical humor and sharp political commentary.
  • 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_69e0b4c1164881909a3bf1e3ddb2bc32 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6bea842dc81908106a0c29d1577aa completed April 21, 2026, 12:02 a.m.
Created at: April 16, 2026, 11:45 a.m.