Triple

T19153333
Position Surface form Disambiguated ID Type / Status
Subject Pro12 E468861 entity
Predicate sponsor P67 FINISHED
Object Guinness 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: Guinness | Statement: [Pro12, sponsor, Guinness]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Guinness
Context triple: [Pro12, sponsor, Guinness]
  • A. Guinness chosen
    Guinness is a world-famous Irish dry stout brand originating from Dublin and known for its dark color, creamy head, and long brewing heritage.
  • B. Kilkenny beer
    Kilkenny beer is an Irish cream ale known for its smooth, creamy head and rich, malty flavor, originating from the historic Smithwick's brewery in Kilkenny, Ireland.
  • C. Carling
    Carling is a major British beer brand known for its long-standing sponsorship of top-tier English football competitions and awards.
  • D. Carling
    Carling is a commune in northeastern France, known historically for its coal mining and industrial activity in the Moselle department.
  • E. Bulmer
    Bulmer is a small village and civil parish in North Yorkshire, England, known for its rural character and historic setting within the Ryedale district.
  • 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_69d8dd084ff48190ac0f8c46ee722629 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5eeb7575c8190b52a9d2bde5ac288 completed April 20, 2026, 9:15 a.m.
Created at: April 10, 2026, 12:06 p.m.