Triple

T19981413
Position Surface form Disambiguated ID Type / Status
Subject Touchstone E493822 entity
Predicate marries P23691 FINISHED
Object Audrey 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: Audrey | Statement: [Touchstone, marries, Audrey]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Audrey
Context triple: [Touchstone, marries, Audrey]
  • A. Audrey
    Audrey is a kind-hearted, nature-loving girl in the 2012 animated film "The Lorax" whose dream of seeing real trees inspires the protagonist’s quest.
  • B. Audrey
    Audrey is the sweet but beleaguered love interest and florist’s assistant in the horror-comedy musical "Little Shop of Horrors."
  • C. Audrey chosen
    Audrey is a simple, rustic shepherdess who serves as a comic character in William Shakespeare’s pastoral comedy "As You Like It."
  • D. Audrey
    Audrey is a feminine given name of Old English origin, traditionally meaning "noble strength" and borne by numerous notable figures in politics, arts, and entertainment.
  • E. Audrey Bernhardt
    Audrey Bernhardt is a key character in the crime drama series "Sneaky Pete," serving as the sharp, resilient matriarch of the Bernhardt family whose business and personal life become entangled with the show's central con artist.
  • 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_69da626a67648190af9653832a3aeced completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e65d13a8a88190bf5f4f697793f4c9 completed April 20, 2026, 5:06 p.m.
Created at: April 11, 2026, 3:28 p.m.