Triple

T15618017
Position Surface form Disambiguated ID Type / Status
Subject Krista E375468 entity
Predicate relatedName P3889 FINISHED
Object Kristy E604457 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: Kristy | Statement: [Krista, relatedName, Kristy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kristy
Context triple: [Krista, relatedName, Kristy]
  • A. Kristy chosen
    Kristy is a 2014 American horror-thriller film starring Haley Bennett as a college student terrorized by a violent cult during a holiday break on an almost-empty campus.
  • B. Kristi
    Kristi is a feminine given name commonly used in English-speaking countries, often as a variant of Kristy or Christina.
  • C. Kristen
    Kristen is the birth name of Kris Jenner, the American television personality and matriarch of the Kardashian–Jenner family.
  • D. Kristen
    Kristen is the central protagonist of the psychological horror film "The Ward," around whom the mysterious and unsettling events of the story revolve.
  • E. Kristen
    Kristen is a central female character in the romantic comedy film "Think Like a Man," whose love life and personal growth are explored through the movie’s ensemble relationship dynamics.
  • 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_69d85ccf2794819096cda4cbcb02d478 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04e997ce481909b2f10d25705fbc6 completed April 16, 2026, 2:51 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff997b9c9081908f6a68e28a50a359 completed May 9, 2026, 8:30 p.m.
Created at: April 10, 2026, 4:13 a.m.