Triple

T22684109
Position Surface form Disambiguated ID Type / Status
Subject 稚内市 E560862 entity
Predicate airportIATA P418 FINISHED
Object WKJ
WKJ is the IATA airport code for Wakkanai Airport, a regional airport serving Wakkanai in northern Hokkaido, Japan.
 E1549492 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: WKJ | Statement: [稚内市, airportIATA, WKJ]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: WKJ
Context triple: [稚内市, airportIATA, WKJ]
  • A. KWJ
    KWJ is the IATA airport code for Gwangju Airport, a regional airport serving the city of Gwangju in South Korea.
  • B. KWN
    KWN is the National Rail station code for Kilwinning railway station in North Ayrshire, Scotland.
  • C. WMKJ
    WMKJ is the ICAO airport code for Senai International Airport, a major airport serving Johor Bahru in southern Malaysia.
  • D. WKG
    WKG is the National Rail station code for Workington railway station in Cumbria, England.
  • E. WKI
    WKI is a German research institute specializing in wood science and wood-based materials, operating under the Fraunhofer Society.
  • 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: WKJ
Triple: [稚内市, airportIATA, WKJ]
Generated description
WKJ is the IATA airport code for Wakkanai Airport, a regional airport serving Wakkanai in northern Hokkaido, Japan.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: WKJ
Target entity description: WKJ is the IATA airport code for Wakkanai Airport, a regional airport serving Wakkanai in northern Hokkaido, Japan.
  • A. KWJ
    KWJ is the IATA airport code for Gwangju Airport, a regional airport serving the city of Gwangju in South Korea.
  • B. KWN
    KWN is the National Rail station code for Kilwinning railway station in North Ayrshire, Scotland.
  • C. WMKJ
    WMKJ is the ICAO airport code for Senai International Airport, a major airport serving Johor Bahru in southern Malaysia.
  • D. WKG
    WKG is the National Rail station code for Workington railway station in Cumbria, England.
  • E. WKI
    WKI is a German research institute specializing in wood science and wood-based materials, operating under the Fraunhofer Society.
  • 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_69e2454d71b48190a1f80af9f82b6fcf completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f17862c8a48190912a8ad09dfda795 completed April 29, 2026, 3:17 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b73f4db988190a651faf7f454c6c8 completed May 18, 2026, 8:17 p.m.
NEDg Description generation batch_6a0b7551043c81908323a86af4db77ce completed May 18, 2026, 8:23 p.m.
NED2 Entity disambiguation (via description) batch_6a0b764c2de88190bb1024206607d107 completed May 18, 2026, 8:27 p.m.
Created at: April 17, 2026, 3:12 p.m.