Triple

T20679680
Position Surface form Disambiguated ID Type / Status
Subject Swedish Match AB E508256 entity
Predicate brand P1500 FINISHED
Object ZYN 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: ZYN | Statement: [Swedish Match AB, brand, ZYN]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ZYN
Context triple: [Swedish Match AB, brand, ZYN]
  • A. ZYN chosen
    ZYN is a popular brand of nicotine pouches known for offering tobacco-free, spit-free oral nicotine products in various flavors and strengths.
  • B. Juul
    Juul is a popular but controversial electronic cigarette brand known for its sleek USB-like design and significant role in the rise of youth vaping.
  • C. NJOY
    NJOY is an American e-cigarette and vaping brand known for producing electronic nicotine delivery systems as an alternative to traditional cigarettes.
  • D. Cigaret
    Cigaret is a brash, young hobo who serves as a central foil and apprentice figure to the seasoned drifter A No. 1 in the 1973 film "Emperor of the North."
  • E. Hooka
    "Hooka" is a reggaeton song by Puerto Rican artist Don Omar, recognized for its catchy rhythm and club-oriented style within his musical catalog.
  • 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_69e0b4c1164881909a3bf1e3ddb2bc32 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6bea516b88190b3e90d03fa981a44 completed April 21, 2026, 12:02 a.m.
Created at: April 16, 2026, 11:44 a.m.