Triple

T12420576
Position Surface form Disambiguated ID Type / Status
Subject Leverkusen E296756 entity
Predicate hasStadium P105 FINISHED
Object BayArena E923559 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: BayArena | Statement: [Leverkusen, hasStadium, BayArena]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: BayArena
Context triple: [Leverkusen, hasStadium, BayArena]
  • A. BayArena chosen
    BayArena is a modern football stadium in Leverkusen, Germany, primarily known as the home ground of Bundesliga club Bayer 04 Leverkusen.
  • B. O.co Coliseum
    O.co Coliseum is a multi-purpose stadium in Oakland, California, historically known for hosting Major League Baseball’s Oakland Athletics and the NFL’s Oakland Raiders.
  • C. Avaya Stadium
    Avaya Stadium was the original name of PayPal Park, a soccer-specific stadium in San Jose, California that serves as the home of the San Jose Earthquakes of Major League Soccer.
  • D. Allianz Stadium
    Allianz Stadium is a modern football arena in Turin, Italy, best known as the home ground of Serie A club Juventus FC.
  • E. Allianz Stadium
    Allianz Stadium is a major sports venue in Sydney, Australia, best known for hosting high-profile rugby union, rugby league, and football (soccer) matches.
  • 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_69d6ada0640c81908c061d7fb3d47786 completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d94d6efd748190a5d9396a343e41e1 completed April 10, 2026, 7:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69f634933b9881909fd592ede7c3e49c completed May 2, 2026, 5:29 p.m.
Created at: April 8, 2026, 9:55 p.m.