Triple

T15927406
Position Surface form Disambiguated ID Type / Status
Subject Marnie E386237 entity
Predicate authorOfSourceWork P2353 FINISHED
Object Winston Graham E968358 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: Winston Graham | Statement: [Marnie, authorOfSourceWork, Winston Graham]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Winston Graham
Context triple: [Marnie, authorOfSourceWork, Winston Graham]
  • A. Winston Graham chosen
    Winston Graham was a British novelist best known for writing the historical Poldark series set in 18th-century Cornwall.
  • B. Jeffrey Archer
    Jeffrey Archer is a British author and former politician best known for his bestselling novels and thrillers.
  • C. Richard Hughes
    Richard Hughes is an English drummer best known as a founding member of the alternative rock band Keane.
  • D. Richard Hughes
    Richard Hughes is a British economist and civil servant who serves as the head of the UK's independent fiscal watchdog, overseeing analysis of the government's public finances and economic forecasts.
  • E. William Boyd
    William Boyd was an American actor best known for portraying the cowboy hero Hopalong Cassidy in numerous films and early television.
  • 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_69d86da750008190987eb26be3f6c118 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e156872964819083a2fb9f86df61ba completed April 16, 2026, 9:37 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffb5b0833081909668c042234b5b75 completed May 9, 2026, 10:31 p.m.
Created at: April 10, 2026, 4:52 a.m.