Triple

T22240316
Position Surface form Disambiguated ID Type / Status
Subject KER E549700 entity
Predicate hasUnderlyingBrand P6092 FINISHED
Object Qeelin 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: Qeelin | Statement: [KER, hasUnderlyingBrand, Qeelin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Qeelin
Context triple: [KER, hasUnderlyingBrand, Qeelin]
  • A. Qeelin chosen
    Qeelin is a contemporary fine jewelry brand known for blending Chinese cultural symbolism with modern design, operating as part of the French luxury group Kering.
  • B. Jewelee
    Jewelee is a DC Comics supervillain and member of the Suicide Squad, often depicted as a jewel-themed criminal partnered with her lover Punch.
  • C. Inkoo
    Inkoo is a coastal municipality in southern Finland known for its bilingual Finnish-Swedish community and location along the Gulf of Finland.
  • D. Woorim
    Woorim is a coastal suburb on Bribie Island in Queensland, Australia, known for its surf beach and relaxed seaside atmosphere.
  • E. Jinyu
    Jinyu is a major variety of the Jin group of Chinese dialects spoken primarily in northern China, especially in Shanxi and surrounding regions.
  • 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_69e11e4102b881909cf47d3768e25c19 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f132133b908190b0fb32a5ee68e1e6 completed April 28, 2026, 10:17 p.m.
Created at: April 16, 2026, 8:38 p.m.