Triple

T20288013
Position Surface form Disambiguated ID Type / Status
Subject Ceres Park E509940 entity
Predicate formerName P65 FINISHED
Object Aarhus Stadion
Aarhus Stadion is a multi-purpose sports stadium in Aarhus, Denmark, primarily used for football and athletics events.
E1422335 NE FINISHED

How this triple was built (4 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: Aarhus Stadion | Statement: [Ceres Park, formerName, Aarhus Stadion]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Aarhus Stadion
Context triple: [Ceres Park, formerName, Aarhus Stadion]
  • A. Vejle Stadium
    Vejle Stadium is a multi-purpose sports arena in Vejle, Denmark, best known as the home ground of the football club Vejle Boldklub.
  • B. Ullevaal Stadion
    Ullevaal Stadion is Norway’s national football stadium and a major sports and events arena located in Oslo.
  • C. Gjemselund Stadion
    Gjemselund Stadion is a football stadium in Kongsvinger, Norway, primarily known as the home venue of the local professional club.
  • D. Marienlyst Stadion
    Marienlyst Stadion is a football stadium in Drammen, Norway, best known as the long-time home ground of the Norwegian club Strømsgodset Toppfotball.
  • E. Henningsvær Stadion
    Henningsvær Stadion is a small, picturesque football pitch in Norway famous for its dramatic setting on a rocky islet surrounded by the sea and mountains in the Lofoten archipelago.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Aarhus Stadion
Triple: [Ceres Park, formerName, Aarhus Stadion]
Generated description
Aarhus Stadion is a multi-purpose sports stadium in Aarhus, Denmark, primarily used for football and athletics events.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Aarhus Stadion
Target entity description: Aarhus Stadion is a multi-purpose sports stadium in Aarhus, Denmark, primarily used for football and athletics events.
  • A. Vejle Stadium
    Vejle Stadium is a multi-purpose sports arena in Vejle, Denmark, best known as the home ground of the football club Vejle Boldklub.
  • B. Ullevaal Stadion
    Ullevaal Stadion is Norway’s national football stadium and a major sports and events arena located in Oslo.
  • C. Gjemselund Stadion
    Gjemselund Stadion is a football stadium in Kongsvinger, Norway, primarily known as the home venue of the local professional club.
  • D. Marienlyst Stadion
    Marienlyst Stadion is a football stadium in Drammen, Norway, best known as the long-time home ground of the Norwegian club Strømsgodset Toppfotball.
  • E. Henningsvær Stadion
    Henningsvær Stadion is a small, picturesque football pitch in Norway famous for its dramatic setting on a rocky islet surrounded by the sea and mountains in the Lofoten archipelago.
  • F. None of above. chosen

Provenance (5 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_69e0b4c652388190b782cad965e5a098 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6769414488190b38e07fd1e989aba completed April 20, 2026, 6:55 p.m.
NED1 Entity disambiguation (via context triple) batch_6a085a2bbcc8819092432b45bebafde6 completed May 16, 2026, 11:51 a.m.
NEDg Description generation batch_6a085ac5b5f4819083c4d12e9cabc758 completed May 16, 2026, 11:53 a.m.
NED2 Entity disambiguation (via description) batch_6a085bc0781c81909fc53a83291badc0 completed May 16, 2026, 11:57 a.m.
Created at: April 16, 2026, 11:09 a.m.