Triple

T9936945
Position Surface form Disambiguated ID Type / Status
Subject Girl, Interrupted E193982 entity
Predicate character P662 FINISHED
Object Susanna Kaysen E831340 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: Susanna Kaysen | Statement: [Girl, Interrupted, character, Susanna Kaysen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Susanna Kaysen
Context triple: [Girl, Interrupted, character, Susanna Kaysen]
  • A. Susanna Kaysen chosen
    Susanna Kaysen is an American writer best known for her memoir "Girl, Interrupted," which recounts her experiences in a psychiatric hospital in the 1960s.
  • B. Meredith Logue
    Meredith Logue is a fictional wealthy socialite character portrayed by Cate Blanchett in the 1999 film "The Talented Mr. Ripley."
  • C. Rosalyn Tureck
    Rosalyn Tureck was an American pianist and harpsichordist renowned for her pioneering, intellectually rigorous interpretations of Johann Sebastian Bach’s keyboard works.
  • D. Lili Jellinek
    Lili Jellinek was a member of the Jellinek family associated with the early history of the Mercedes automobile brand.
  • E. Sybil Newman
    Sybil Newman is known as the former spouse of American screenwriter and producer William Broyles Jr.
  • 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_69ca82e409348190a393777356b80a2a completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cdb5e4e19881909879b394090d6629 completed April 2, 2026, 12:18 a.m.
NED1 Entity disambiguation (via context triple) batch_69d23d4528108190b38111bb36832a67 completed April 5, 2026, 10:45 a.m.
Created at: March 30, 2026, 8:44 p.m.