Triple

T9705675
Position Surface form Disambiguated ID Type / Status
Subject Kinmen Airport E234891 entity
Predicate IATAcode P418 FINISHED
Object KNH
KNH is the IATA airport code for Kinmen Airport, which serves Kinmen Island off the coast of southeastern China and is administered by Taiwan.
 E815207 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: KNH | Statement: [Kinmen Airport, IATAcode, KNH]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: KNH
Context triple: [Kinmen Airport, IATAcode, KNH]
  • A. KNBH
    KNBH was the original call sign of the Los Angeles television station now known as KNBC-TV, the NBC owned-and-operated flagship on the West Coast.
  • B. KRH
    KRH is the commonly used abbreviation for the King’s Royal Hussars, a British Army cavalry regiment.
  • C. HKNW
    HKNW is the ICAO airport code assigned to Wilson Airport in Nairobi, Kenya.
  • D. KHC
    KHC is a selective interdisciplinary honors college at Boston University that offers an enriched curriculum and close-knit academic community for high-achieving undergraduates.
  • E. KNO
    KNO is the IATA airport code for Kualanamu International Airport serving Medan and the surrounding region in North Sumatra, Indonesia.
  • 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: KNH
Triple: [Kinmen Airport, IATAcode, KNH]
Generated description
KNH is the IATA airport code for Kinmen Airport, which serves Kinmen Island off the coast of southeastern China and is administered by Taiwan.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: KNH
Target entity description: KNH is the IATA airport code for Kinmen Airport, which serves Kinmen Island off the coast of southeastern China and is administered by Taiwan.
  • A. KNBH
    KNBH was the original call sign of the Los Angeles television station now known as KNBC-TV, the NBC owned-and-operated flagship on the West Coast.
  • B. KRH
    KRH is the commonly used abbreviation for the King’s Royal Hussars, a British Army cavalry regiment.
  • C. HKNW
    HKNW is the ICAO airport code assigned to Wilson Airport in Nairobi, Kenya.
  • D. KHC
    KHC is a selective interdisciplinary honors college at Boston University that offers an enriched curriculum and close-knit academic community for high-achieving undergraduates.
  • E. KNO
    KNO is the IATA airport code for Kualanamu International Airport serving Medan and the surrounding region in North Sumatra, Indonesia.
  • 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_69ca84cc78808190a56f3402b7c139a7 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cd9da369b4819081f6ce01289ed725 completed April 1, 2026, 10:35 p.m.
NED1 Entity disambiguation (via context triple) batch_69d19136b40c8190922052dd84d49f15 completed April 4, 2026, 10:31 p.m.
NEDg Description generation batch_69d193623fac8190a8dcdac664a977f3 completed April 4, 2026, 10:40 p.m.
NED2 Entity disambiguation (via description) batch_69d193cc61208190b98fe862b295dda3 completed April 4, 2026, 10:42 p.m.
Created at: March 30, 2026, 8:19 p.m.