Triple

T13675786
Position Surface form Disambiguated ID Type / Status
Subject Arcadia E327872 entity
Predicate hasCharacter P2308 FINISHED
Object Lady Croom E873518 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: Lady Croom | Statement: [Arcadia, hasCharacter, Lady Croom]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lady Croom
Context triple: [Arcadia, hasCharacter, Lady Croom]
  • A. Lady Croom chosen
    Lady Croom is the witty, aristocratic mistress of Sidley Park in Tom Stoppard’s play "Arcadia," embodying Regency-era elegance, vanity, and social authority.
  • B. Lady Glencora
    Lady Glencora is a spirited and politically influential aristocratic heroine in Anthony Trollope’s Palliser novels, known for her wit, impulsiveness, and complex marriage to Plantagenet Palliser.
  • C. The Lady Dannatt
    The Lady Dannatt is a British public figure and representative of the Crown who serves as the ceremonial head of the county of Norfolk.
  • D. Lady Mont
    Lady Mont is the central figure in the story "Maid in Waiting," around whom the novel’s events and relationships revolve.
  • E. Lady Lieutenant
    Lady Lieutenant is the female title used for the monarch’s personal representative in a given county or area in the United Kingdom.
  • 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_69d8076f1fa8819094664a59b55010df completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbc65c04988190b675e6fb7241e53c completed April 12, 2026, 4:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69f7943dbf748190b41abfe9d81d1427 completed May 3, 2026, 6:30 p.m.
Created at: April 9, 2026, 9:53 p.m.