Triple

T21678491
Position Surface form Disambiguated ID Type / Status
Subject Carly E535037 entity
Predicate hasVariant P455 FINISHED
Object Karlie 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: Karlie | Statement: [Carly, hasVariant, Karlie]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Karlie
Context triple: [Carly, hasVariant, Karlie]
  • A. Karlie Kloss chosen
    Karlie Kloss is an American fashion model and entrepreneur known for her high-profile runway work, including with major luxury brands, and for founding the coding education initiative Kode With Klossy.
  • B. Kendall Jenner
    Kendall Jenner is an American fashion model and television personality who rose to fame on "Keeping Up with the Kardashians" and has become one of the world's most recognizable runway and editorial models.
  • C. Bella Hadid
    Bella Hadid is an American fashion model known for her work with major luxury brands and frequent appearances on international Vogue covers.
  • D. Kylie Jenner
    Kylie Jenner is an American media personality, cosmetics entrepreneur, and member of the Kardashian–Jenner family, widely known for her role on "Keeping Up with the Kardashians" and for founding Kylie Cosmetics.
  • E. Gigi Hadid
    Gigi Hadid is an American fashion model and television personality who has become one of the most recognizable faces in the global modeling industry.
  • 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_69e0c469b6ec8190aee4cadd1527db91 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ef8a11088081908911af2629f54c1c completed April 27, 2026, 4:08 p.m.
Created at: April 16, 2026, 6:43 p.m.