Triple

T11115627
Position Surface form Disambiguated ID Type / Status
Subject Nicorette E262877 entity
Predicate offersProduct P10882 FINISHED
Object Nicorette lozenges E262877 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: Nicorette lozenges | Statement: [Nicorette, offersProduct, Nicorette lozenges]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nicorette lozenges
Context triple: [Nicorette, offersProduct, Nicorette lozenges]
  • A. Nicorette chosen
    Nicorette is a leading nicotine replacement therapy brand offering products like gum, lozenges, and patches to help people quit smoking.
  • B. L&M Menthol
    L&M Menthol is a menthol-flavored variant of the L&M cigarette brand, offering a cooler, minty smoking experience.
  • C. Altoids
    Altoids are a long-standing brand of strong, peppermint-flavored mints popularly marketed as "Curiously Strong" and sold in distinctive metal tins.
  • D. Parliament Menthol
    Parliament Menthol is a menthol-flavored variant of Parliament cigarettes known for its recessed filter and smoother, minty taste.
  • E. Läkerol
    Läkerol is a well-known Scandinavian brand of sugar-free pastilles and throat lozenges, recognized for its wide range of flavors and long-standing presence in Nordic confectionery.
  • 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_69d6aa9b46cc8190b19f9f0cc45bf322 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d79aa7254c8190abce35696ad2be03 completed April 9, 2026, 12:25 p.m.
NED1 Entity disambiguation (via context triple) batch_69e441cb16bc81908b5321506f655e38 completed April 19, 2026, 2:45 a.m.
Created at: April 8, 2026, 9:27 p.m.