Triple

T9152123
Position Surface form Disambiguated ID Type / Status
Subject Sophie MacDonald E219610 entity
Predicate relationshipWith P10260 FINISHED
Object Isabel Bradley E229195 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: Isabel Bradley | Statement: [Sophie MacDonald, relationshipWith, Isabel Bradley]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Isabel Bradley
Context triple: [Sophie MacDonald, relationshipWith, Isabel Bradley]
  • A. Isabel Bradley chosen
    Isabel Bradley is a central character in the 1946 film adaptation of W. Somerset Maugham's "The Razor's Edge," known as a sophisticated, ambitious socialite whose choices profoundly affect the protagonist's spiritual journey.
  • B. Isabel Robey
    Isabel Robey was one of the accused women in the early 17th-century Pendle witch trials, a notorious series of English witchcraft prosecutions.
  • C. Isabel Wilson
    Isabel Wilson was the first wife of American pop artist Roy Lichtenstein, married to him during the early years of his career.
  • D. Grace Bradley
    Grace Bradley was an American film actress and dancer best known for her roles in 1930s Hollywood comedies and musicals.
  • E. Isabel Lucas
    Isabel Lucas is an Australian actress known for her roles in films such as "Transformers: Revenge of the Fallen," "Immortals," and various Australian television series.
  • 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_69ca83e25418819093c6503deeaf30de completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cca96cf4548190a3a45172f0e9d0ec completed April 1, 2026, 5:13 a.m.
NED1 Entity disambiguation (via context triple) batch_69d0c6fd5d4481909300c5101304f35f completed April 4, 2026, 8:08 a.m.
Created at: March 30, 2026, 7:20 p.m.