Triple

T15941389
Position Surface form Disambiguated ID Type / Status
Subject Thomas Hardy E386571 entity
Predicate spouse P13 FINISHED
Object Florence Dugdale 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: Florence Dugdale | Statement: [Thomas Hardy, spouse, Florence Dugdale]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Florence Dugdale
Context triple: [Thomas Hardy, spouse, Florence Dugdale]
  • A. Florence Dugdale chosen
    Florence Dugdale was an English schoolteacher and writer best known as the second wife and later biographer of novelist and poet Thomas Hardy.
  • B. Florence Craye
    Florence Craye is a recurring character in P. G. Wodehouse’s Jeeves and Wooster stories, known as an earnest, intellectual young woman and one of Bertie Wooster’s on-and-off fiancées.
  • C. Florence Winnifrith
    Florence Winnifrith is the mother of British actress Anna Lee.
  • D. Florence Gwendoline Cayzer
    Florence Gwendoline Cayzer was a British aristocrat best known as the wife of Admiral of the Fleet John Jellicoe, 1st Earl Jellicoe, a leading Royal Navy commander during World War I.
  • E. Florence Farr
    Florence Farr was a British actress, writer, and occultist closely associated with the late Victorian esoteric and literary circles, including figures like W.B. Yeats.
  • 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_69d86da750008190987eb26be3f6c118 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e156ce0230819089a20114a755a75a completed April 16, 2026, 9:38 p.m.
Created at: April 10, 2026, 4:53 a.m.