Triple

T7891798
Position Surface form Disambiguated ID Type / Status
Subject AB InBev E183252 entity
Predicate brand P1500 FINISHED
Object Quilmes E420675 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: Quilmes | Statement: [AB InBev, brand, Quilmes]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Quilmes
Context triple: [AB InBev, brand, Quilmes]
  • A. Quilmes chosen
    Quilmes is a city in the Greater Buenos Aires metropolitan area of Argentina, known for its industrial activity and as the namesake of one of the country’s most popular beer brands.
  • B. Birra Moretti
    Birra Moretti is a traditional Italian beer brand known for its classic lager and iconic mustachioed man logo, now distributed internationally.
  • C. Jupiler
    Jupiler is a popular Belgian pilsner beer brand widely known for its strong association with football and major sports sponsorships.
  • D. Corona Refresca
    Corona Refresca is a line of tropical, fruit-flavored alcoholic beverages from the Corona brand, designed as light, refreshing alternatives to traditional beer.
  • E. Carling
    Carling is a major British beer brand known for its long-standing sponsorship of top-tier English football competitions and awards.
  • 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_69ca828c474c8190a254d6499871eaff completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cb39fef2e48190a6282c217c33c57a completed March 31, 2026, 3:05 a.m.
NED1 Entity disambiguation (via context triple) batch_69cb5ba51ee48190b654a931da2c049f completed March 31, 2026, 5:29 a.m.
Created at: March 30, 2026, 5 p.m.