Triple

T7646858
Position Surface form Disambiguated ID Type / Status
Subject Korea Airports Corporation E173146 entity
Predicate abbreviation P43 FINISHED
Object KAC
KAC is the acronym for Korea Airports Corporation, the South Korean government-owned company that manages and operates many of the nation’s domestic airports.
 E680206 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: KAC | Statement: [Korea Airports Corporation, abbreviation, KAC]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: KAC
Context triple: [Korea Airports Corporation, abbreviation, KAC]
  • A. KCAK
    KCAK is the ICAO airport code for Akron–Canton Airport, a commercial airport serving the Akron and Canton regions of Ohio, USA.
  • B. KCA
    KCA is a nonprofit organization dedicated to providing life-saving HIV treatment, care, and support to children and families in underserved communities, particularly in Africa and India.
  • C. Kac
    Kac is a surname most notably associated with Polish-American mathematician Mark Kac, known for his work in probability theory and mathematical physics.
  • D. KLAC
    KLAC is a Los Angeles-based sports radio station best known for broadcasting Los Angeles Lakers games and other local sports coverage.
  • E. KA
    KA is the vehicle registration code used on license plates for cars registered in the German city of Karlsruhe.
  • 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: KAC
Triple: [Korea Airports Corporation, abbreviation, KAC]
Generated description
KAC is the acronym for Korea Airports Corporation, the South Korean government-owned company that manages and operates many of the nation’s domestic airports.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: KAC
Target entity description: KAC is the acronym for Korea Airports Corporation, the South Korean government-owned company that manages and operates many of the nation’s domestic airports.
  • A. KCAK
    KCAK is the ICAO airport code for Akron–Canton Airport, a commercial airport serving the Akron and Canton regions of Ohio, USA.
  • B. KCA
    KCA is a nonprofit organization dedicated to providing life-saving HIV treatment, care, and support to children and families in underserved communities, particularly in Africa and India.
  • C. Kac
    Kac is a surname most notably associated with Polish-American mathematician Mark Kac, known for his work in probability theory and mathematical physics.
  • D. KLAC
    KLAC is a Los Angeles-based sports radio station best known for broadcasting Los Angeles Lakers games and other local sports coverage.
  • E. KA
    KA is the vehicle registration code used on license plates for cars registered in the German city of Karlsruhe.
  • 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_69c6995360188190968ee57b72a1627f completed March 27, 2026, 2:50 p.m.
NER Named-entity recognition batch_69c6faf3bd388190a8cb0f13322a7c00 completed March 27, 2026, 9:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69c89ad236448190886611ac9d1cc393 completed March 29, 2026, 3:21 a.m.
NEDg Description generation batch_69c89b8a06588190b05a8ee7ddbe737c completed March 29, 2026, 3:24 a.m.
NED2 Entity disambiguation (via description) batch_69c89c1284708190bb2707e41de3be85 completed March 29, 2026, 3:27 a.m.
Created at: March 27, 2026, 3:58 p.m.