Triple

T22101318
Position Surface form Disambiguated ID Type / Status
Subject Saraband for Dead Lovers E546177 entity
Predicate authorOfSourceWork P2353 FINISHED
Object Helen Simpson 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: Helen Simpson | Statement: [Saraband for Dead Lovers, authorOfSourceWork, Helen Simpson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Helen Simpson
Context triple: [Saraband for Dead Lovers, authorOfSourceWork, Helen Simpson]
  • A. Helen Simpson chosen
    Helen Simpson was an Australian-born British novelist and playwright active in the early 20th century, known for her crime and historical fiction.
  • B. Paula Southgate
    Paula Southgate is a New Zealand local-body politician who serves as the mayor of Hamilton, one of the country’s major urban centers.
  • C. Caroline Mould
    Caroline Mould is a British racehorse owner best known for owning the champion National Hunt racehorse Sprinter Sacre.
  • D. Sarah Neesham
    Sarah Neesham was the wife of George Jeffreys, the notorious 17th-century English judge known as "Judge Jeffreys."
  • E. Rachel Kempson
    Rachel Kempson was an English actress and matriarch of the Redgrave acting family, known for her extensive stage and film career.
  • 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_69e11e378dc08190896d6a51597afd5a completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f1291501508190ad5689be5abb2ba6 completed April 28, 2026, 9:39 p.m.
Created at: April 16, 2026, 8:30 p.m.