Triple

T18167550
Position Surface form Disambiguated ID Type / Status
Subject Gerald du Maurier E434932 entity
Predicate familyName P18 FINISHED
Object du Maurier 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: du Maurier | Statement: [Gerald du Maurier, familyName, du Maurier]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: du Maurier
Context triple: [Gerald du Maurier, familyName, du Maurier]
  • A. Daphne du Maurier
    Daphne du Maurier was a British novelist and playwright best known for her atmospheric works of psychological suspense, including "Rebecca" and "Jamaica Inn."
  • B. Angela du Maurier
    Angela du Maurier was a British writer and actress, best known as the lesser-known but also literary sister of novelist Daphne du Maurier.
  • C. Gerald du Maurier chosen
    Gerald du Maurier was a prominent early 20th-century English actor-manager known for his subtle, naturalistic acting style and influential leadership in the London theatre scene.
  • 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. David Garnett
    David Garnett was a British writer and publisher associated with the Bloomsbury Group, known for novels such as "Lady into Fox" and "Aspects of Love."
  • 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_69d8b90b7a188190b3fc7b8d4a6cd20a completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4df52f8b08190ab2c4d76b510cd28 completed April 19, 2026, 1:57 p.m.
Created at: April 10, 2026, 10:30 a.m.