Triple

T20890131
Position Surface form Disambiguated ID Type / Status
Subject Lolly Willowes E514385 entity
Predicate hasCharacter P2308 FINISHED
Object Laura Willowes 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: Laura Willowes | Statement: [Lolly Willowes, hasCharacter, Laura Willowes]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Laura Willowes
Context triple: [Lolly Willowes, hasCharacter, Laura Willowes]
  • A. Laura Willowes chosen
    Laura Willowes is the quietly rebellious English spinster in Sylvia Townsend Warner’s novel who escapes her stifling family life by embracing witchcraft and independence in the countryside.
  • B. Mariette Larkin
    Mariette Larkin is the charming, free-spirited eldest daughter of the Larkin family in H.E. Bates’s rural English comedy series "The Darling Buds of May."
  • C. Elizabeth Layton
    Elizabeth Layton is Winston Churchill’s young personal secretary and typist, depicted as a close and observant aide during the early years of World War II.
  • D. Jocelyn Harris
    Jocelyn Harris is a fictional character portrayed by actress Alona Tal, best known from her role in the television series "Veronica Mars."
  • E. Katherine Warren
    Katherine Warren was an American character actress known for her supporting roles in mid-20th-century films and television.
  • 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_69e0b4f7ebe48190952a85547a0f31a1 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6d05d591481908c9c999db76760fc completed April 21, 2026, 1:18 a.m.
Created at: April 16, 2026, 12:46 p.m.