Triple

T6708909
Position Surface form Disambiguated ID Type / Status
Subject Mannheim E153078 entity
Predicate hasLandmark P105 FINISHED
Object SAP Arena E398229 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: SAP Arena | Statement: [Mannheim, hasLandmark, SAP Arena]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: SAP Arena
Context triple: [Mannheim, hasLandmark, SAP Arena]
  • A. SAP Arena chosen
    SAP Arena is a multi-purpose indoor arena in Mannheim, Germany, best known as a major venue for ice hockey, concerts, and other large-scale events.
  • B. Volkswagen Arena
    Volkswagen Arena is a modern football stadium in Wolfsburg, Germany, best known as the home ground of the Bundesliga club VfL Wolfsburg.
  • C. Commerzbank-Arena
    Commerzbank-Arena is a major football and multi-purpose stadium in Frankfurt, Germany, best known as the longtime home ground of Eintracht Frankfurt and a venue for international sporting and entertainment events.
  • D. Voith-Arena
    Voith-Arena is a football stadium in Heidenheim, Germany, primarily known as the venue for 1. FC Heidenheim’s home matches.
  • E. Lanxess Arena
    Lanxess Arena is a large multi-purpose indoor arena in Cologne, Germany, known for hosting major sports events, concerts, and entertainment shows.
  • 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_69c68808d8d8819087369015270788fe completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d105b49c8190932246a727e2c513 completed March 27, 2026, 6:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7008e6b308190a3d5db2bf4a469c4 completed March 27, 2026, 10:11 p.m.
Created at: March 27, 2026, 2:06 p.m.