Triple

T14311381
Position Surface form Disambiguated ID Type / Status
Subject Enschede E354840 entity
Predicate knownFor P22 FINISHED
Object Grolsch brewery E165339 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: Grolsch brewery | Statement: [Enschede, knownFor, Grolsch brewery]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Grolsch brewery
Context triple: [Enschede, knownFor, Grolsch brewery]
  • A. Grolsch chosen
    Grolsch is a Dutch brewery best known for its distinctive swing-top bottled beers and long-standing presence in the international beer market.
  • B. Knooppunt Amstel
    Knooppunt Amstel is a major motorway interchange in Amsterdam that connects the A10 ring road with other key highways and routes into the city.
  • C. Jopenkerk brewery
    Jopenkerk brewery is a craft brewery and brewpub housed in a converted former church in Haarlem, the Netherlands, known for its specialty beers and distinctive setting.
  • D. Heineken N.V.
    Heineken N.V. is a major Dutch multinational brewing company best known for producing Heineken beer and owning numerous breweries and beer brands worldwide.
  • E. Heineken France
    Heineken France is the French brewing and beverage subsidiary of the global Dutch beer company Heineken, responsible for producing, marketing, and distributing its brands in France.
  • 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_69d8278ed42c8190b9f882dcce611347 completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de85b386d0819087d14f3ce84a1997 completed April 14, 2026, 6:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd3d3124488190b2ea35949294e297 completed May 8, 2026, 1:32 a.m.
Created at: April 10, 2026, 1:12 a.m.