Triple

T20671304
Position Surface form Disambiguated ID Type / Status
Subject Korona Kielce E508029 entity
Predicate homeStadium P890 FINISHED
Object Suzuki Arena
Suzuki Arena is a football stadium in Kielce, Poland, best known as the home ground of the Polish club Korona Kielce.
E1444798 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: Suzuki Arena | Statement: [Korona Kielce, homeStadium, Suzuki Arena]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Suzuki Arena
Context triple: [Korona Kielce, homeStadium, Suzuki Arena]
  • A. Setsoto Stadium
    Setsoto Stadium is a multi-purpose national sports venue in Maseru, Lesotho, primarily used for football matches and major public events.
  • B. U-Power Stadium
    U-Power Stadium is a football stadium in Monza, Italy, primarily known as the home ground of AC Monza.
  • C. Maishima Arena
    Maishima Arena is an indoor sports venue in Osaka, Japan, primarily known for hosting professional basketball games and other sporting events.
  • D. Ricoh Coliseum
    Ricoh Coliseum is a multi-purpose indoor arena in Toronto, Ontario, best known for hosting ice hockey games and various entertainment events.
  • E. Kawasaki Stadium
    Kawasaki Stadium was a former baseball stadium in Kawasaki, Japan, best known as the longtime home field of Nippon Professional Baseball’s Lotte Orions.
  • 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: Suzuki Arena
Triple: [Korona Kielce, homeStadium, Suzuki Arena]
Generated description
Suzuki Arena is a football stadium in Kielce, Poland, best known as the home ground of the Polish club Korona Kielce.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Suzuki Arena
Target entity description: Suzuki Arena is a football stadium in Kielce, Poland, best known as the home ground of the Polish club Korona Kielce.
  • A. Setsoto Stadium
    Setsoto Stadium is a multi-purpose national sports venue in Maseru, Lesotho, primarily used for football matches and major public events.
  • B. U-Power Stadium
    U-Power Stadium is a football stadium in Monza, Italy, primarily known as the home ground of AC Monza.
  • C. Maishima Arena
    Maishima Arena is an indoor sports venue in Osaka, Japan, primarily known for hosting professional basketball games and other sporting events.
  • D. Ricoh Coliseum
    Ricoh Coliseum is a multi-purpose indoor arena in Toronto, Ontario, best known for hosting ice hockey games and various entertainment events.
  • E. Kawasaki Stadium
    Kawasaki Stadium was a former baseball stadium in Kawasaki, Japan, best known as the longtime home field of Nippon Professional Baseball’s Lotte Orions.
  • 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_69e0b4c1164881909a3bf1e3ddb2bc32 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6b5c92aa8819096fbe0ca5101d01b completed April 20, 2026, 11:24 p.m.
NED1 Entity disambiguation (via context triple) batch_6a08cd64aa4081908cf843a32e99ae01 completed May 16, 2026, 8:02 p.m.
NEDg Description generation batch_6a08d175eefc8190a5178c0f70f7d79f completed May 16, 2026, 8:20 p.m.
NED2 Entity disambiguation (via description) batch_6a08d23e8ac48190be1726c8e4913b1a completed May 16, 2026, 8:23 p.m.
Created at: April 16, 2026, 11:44 a.m.