Triple

T13401370
Position Surface form Disambiguated ID Type / Status
Subject South Korea men's national ice hockey team E319836 entity
Predicate IOCCode P6277 FINISHED
Object KOR
KOR is the International Olympic Committee country code representing South Korea in international sporting events.
 E695351 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: KOR | Statement: [South Korea men's national ice hockey team, IOCCode, KOR]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: KOR
Context triple: [South Korea men's national ice hockey team, IOCCode, KOR]
  • A. KOR
    KOR is the FIFA country code representing the South Korea national football team in international competitions.
  • B. KOR
    KOR is the ICAO airline designator assigned to Air Koryo, the state-owned national carrier of North Korea.
  • C. Kor
    Kor is a prominent Klingon warrior and commander from the Star Trek franchise, known as one of the earliest and most iconic Klingon characters in the series.
  • D. KORL
    KORL is the ICAO airport code for Orlando Executive Airport, a public airport serving the Orlando, Florida area.
  • E. KR
    KR is the stock ticker symbol for The Kroger Co., one of the largest supermarket chains in the United States.
  • 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: KOR
Triple: [South Korea men's national ice hockey team, IOCCode, KOR]
Generated description
KOR is the International Olympic Committee country code representing South Korea in international sporting events.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: KOR
Target entity description: KOR is the International Olympic Committee country code representing South Korea in international sporting events.
  • A. KOR chosen
    KOR is the FIFA country code representing the South Korea national football team in international competitions.
  • B. KOR
    KOR is the ICAO airline designator assigned to Air Koryo, the state-owned national carrier of North Korea.
  • C. Kor
    Kor is a prominent Klingon warrior and commander from the Star Trek franchise, known as one of the earliest and most iconic Klingon characters in the series.
  • D. KORL
    KORL is the ICAO airport code for Orlando Executive Airport, a public airport serving the Orlando, Florida area.
  • E. KR
    KR is the stock ticker symbol for The Kroger Co., one of the largest supermarket chains in the United States.
  • F. None of above.

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_69d806b943cc8190b6af624d385d7e12 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69dbae4982e0819087a9fcb2fa88541f completed April 12, 2026, 2:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69f73076a7ac8190bd7898edff7d90e8 completed May 3, 2026, 11:24 a.m.
NEDg Description generation batch_69f732351cf88190be85186d20b529b7 completed May 3, 2026, 11:32 a.m.
NED2 Entity disambiguation (via description) batch_69f732d82c308190907e11de42e2c8ea completed May 3, 2026, 11:34 a.m.
Created at: April 9, 2026, 9:34 p.m.