Triple

T22413511
Position Surface form Disambiguated ID Type / Status
Subject Crossing a Bridge E554051 entity
Predicate performer P1363 FINISHED
Object Anya (character) 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: Anya (character) | Statement: [Crossing a Bridge, performer, Anya (character)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Anya (character)
Context triple: [Crossing a Bridge, performer, Anya (character)]
  • A. Anya
    Anya is a person known primarily through her relationship to someone named Hannah, likely as a friend or family member.
  • B. Anya chosen
    Anya is the spirited, amnesiac young woman in the animated film "Anastasia" who embarks on a journey to discover whether she is the lost Russian Grand Duchess.
  • C. Anya
    Anya is the given name of actress Anya Taylor-Joy, known for her roles in films like "The Witch" and the series "The Queen's Gambit."
  • D. Anya
    Anya is a novel by Joy Davidman, best known as a work of mid-20th-century fiction by the poet and writer who later married C. S. Lewis.
  • E. Anya
    Anya is a central character in J.M. Coetzee’s novel "Diary of a Bad Year," serving as the young typist whose relationship with the aging writer narrator drives much of the book’s emotional and intellectual tension.
  • 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_69e11e4e6ce8819085a1e06d886bf21c completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f1594496348190ba25dc0193d092f2 completed April 29, 2026, 1:05 a.m.
Created at: April 16, 2026, 8:46 p.m.