Triple

T460296
Position Surface form Disambiguated ID Type / Status
Subject British American Tobacco E7321 entity
Predicate brand P1500 FINISHED
Object glo
glo is a heated tobacco product brand developed by British American Tobacco as an alternative to traditional cigarettes.
 E57778 NE FINISHED

How this triple was built (4 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: glo | Statement: [British American Tobacco, brand, glo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: glo
Context triple: [British American Tobacco, brand, glo]
  • A. GÖ
    GÖ is the vehicle registration code used on license plates for the city and district of Göttingen in Germany.
  • B. GU
    GU is the two-letter ISO 3166 country code assigned to Guam, an unincorporated territory of the United States in the western Pacific Ocean.
  • C. G.O.L.H.
    G.O.L.H. is the abbreviation for the Grand Officier rank, one of the highest grades within France’s prestigious national order, the Légion d'honneur.
  • D. GOS
    GOS is the acronym for the Global Observing System, an international network of instruments and facilities that continuously monitor the Earth's atmosphere, oceans, and land for weather and climate services.
  • E. Gliz
    Gliz is one of the official mascots of the 2006 Winter Olympics in Turin, Italy, depicted as a stylized anthropomorphic ice cube symbolizing winter sports and modernity.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: glo
Triple: [British American Tobacco, brand, glo]
Generated description
glo is a heated tobacco product brand developed by British American Tobacco as an alternative to traditional cigarettes.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: glo
Target entity description: glo is a heated tobacco product brand developed by British American Tobacco as an alternative to traditional cigarettes.
  • A. GÖ
    GÖ is the vehicle registration code used on license plates for the city and district of Göttingen in Germany.
  • B. GU
    GU is the two-letter ISO 3166 country code assigned to Guam, an unincorporated territory of the United States in the western Pacific Ocean.
  • C. G.O.L.H.
    G.O.L.H. is the abbreviation for the Grand Officier rank, one of the highest grades within France’s prestigious national order, the Légion d'honneur.
  • D. GOS
    GOS is the acronym for the Global Observing System, an international network of instruments and facilities that continuously monitor the Earth's atmosphere, oceans, and land for weather and climate services.
  • E. Gliz
    Gliz is one of the official mascots of the 2006 Winter Olympics in Turin, Italy, depicted as a stylized anthropomorphic ice cube symbolizing winter sports and modernity.
  • F. None of above. chosen

Provenance (5 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_69a2e7e5c5bc8190a1dc8178218fba40 completed Feb. 28, 2026, 1:04 p.m.
NER Named-entity recognition batch_69a2efbd6ed481909ec40f12b5b675c8 completed Feb. 28, 2026, 1:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69a44f583ea081908d92fe5b5dc4d3c0 completed March 1, 2026, 2:38 p.m.
NEDg Description generation batch_69a45150b3f8819094519329a68fb1b8 completed March 1, 2026, 2:46 p.m.
NED2 Entity disambiguation (via description) batch_69a451ab785c8190b4cab0d162b4efa8 completed March 1, 2026, 2:48 p.m.
Created at: Feb. 28, 2026, 1:12 p.m.