Triple

T4203269
Position Surface form Disambiguated ID Type / Status
Subject Kagoshima Airport E86120 entity
Predicate IATAcode P418 FINISHED
Object KOJ
KOJ is the three-letter IATA airport code for Kagoshima Airport in Kagoshima Prefecture, Japan.
 E420822 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: KOJ | Statement: [Kagoshima Airport, IATAcode, KOJ]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: KOJ
Context triple: [Kagoshima Airport, IATAcode, KOJ]
  • A. KO
    KO is the New York Stock Exchange ticker symbol for The Coca-Cola Company, one of the world’s largest and most recognizable beverage corporations.
  • B. KOS
    KOS is the vehicle registration code assigned to the town of Oświęcim in southern Poland.
  • C. Kindai
    Kindai is a major private university in Japan known for its comprehensive academic programs and strong research in fields such as science, engineering, and fisheries.
  • D. KCO
    KCO is the abbreviated name commonly used for the Royal Concertgebouw Orchestra, one of the world’s leading symphony orchestras based in Amsterdam.
  • E. Kono
    Kono is a Japanese surname most prominently associated with politician Taro Kono, a leading figure in contemporary Japanese politics.
  • 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: KOJ
Triple: [Kagoshima Airport, IATAcode, KOJ]
Generated description
KOJ is the three-letter IATA airport code for Kagoshima Airport in Kagoshima Prefecture, Japan.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: KOJ
Target entity description: KOJ is the three-letter IATA airport code for Kagoshima Airport in Kagoshima Prefecture, Japan.
  • A. KO
    KO is the New York Stock Exchange ticker symbol for The Coca-Cola Company, one of the world’s largest and most recognizable beverage corporations.
  • B. KOS
    KOS is the vehicle registration code assigned to the town of Oświęcim in southern Poland.
  • C. Kindai
    Kindai is a major private university in Japan known for its comprehensive academic programs and strong research in fields such as science, engineering, and fisheries.
  • D. KCO
    KCO is the abbreviated name commonly used for the Royal Concertgebouw Orchestra, one of the world’s leading symphony orchestras based in Amsterdam.
  • E. Kono
    Kono is a Japanese surname most prominently associated with politician Taro Kono, a leading figure in contemporary Japanese politics.
  • 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_69aed93b89f48190a31f6d57c760e42f completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69af0380d470819091ffdb1161437266 completed March 9, 2026, 5:29 p.m.
NED1 Entity disambiguation (via context triple) batch_69b58a173a78819094915f63c8411602 completed March 14, 2026, 4:17 p.m.
NEDg Description generation batch_69b58e1e7bc08190b75486c74953f609 completed March 14, 2026, 4:34 p.m.
NED2 Entity disambiguation (via description) batch_69b58e7a208481909056b6fba4597bf4 completed March 14, 2026, 4:36 p.m.
Created at: March 9, 2026, 3:49 p.m.