Triple

T20265083
Position Surface form Disambiguated ID Type / Status
Subject Karen Smith E498945 entity
Predicate friendOf P8712 FINISHED
Object Regina George 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: Regina George | Statement: [Karen Smith, friendOf, Regina George]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Regina George
Context triple: [Karen Smith, friendOf, Regina George]
  • A. Regina George chosen
    Regina George is the manipulative and popular queen bee of her high school clique in the teen comedy film "Mean Girls."
  • B. Regina Mills
    Regina Mills is a central character in the fantasy TV series "Once Upon a Time," known as the Evil Queen whose complex journey explores redemption, love, and power.
  • C. Jessica Buchanan
    Jessica Buchanan is a fictional character from the soap opera "One Life to Live," known as the daughter of Viki Lord and central to numerous dramatic storylines involving identity, family, and trauma.
  • D. Emma Wibberly
    Emma Wibberly is a fictional character appearing in John Stephens' fantasy novel "The Fire Chronicle," part of the Books of Beginning series.
  • E. Georgia Simmons
    Georgia Simmons was an actress known for her role in the classic "Twilight Zone" episode "The Bewitchin’ Pool."
  • 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_69da6275fa6c8190952924930adee150 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e674ce27688190b31d7a6c98d3ec5e completed April 20, 2026, 6:47 p.m.
Created at: April 11, 2026, 11:41 p.m.