Triple

T17273493
Position Surface form Disambiguated ID Type / Status
Subject Turku Airport E419324 entity
Predicate IATAcode P418 FINISHED
Object TKU
TKU is the IATA airport code for Turku Airport, a regional international airport serving the city of Turku in southwestern Finland.
E1260361 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: TKU | Statement: [Turku Airport, IATAcode, TKU]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: TKU
Context triple: [Turku Airport, IATAcode, TKU]
  • A. KNTU
    KNTU is the ICAO airport code for Naval Air Station Oceana, a major United States Navy jet base located in Virginia Beach, Virginia.
  • B. TUKE
    TUKE is a major Slovak technical university based in Košice, known for its engineering, technology, and applied science programs.
  • C. KTUL
    KTUL is the ICAO airport code for Tulsa International Airport, a major commercial and military aviation facility serving Tulsa, Oklahoma.
  • D. TKK
    TKK is the IATA airport code for Chuuk International Airport, the main air gateway to Chuuk State in the Federated States of Micronesia.
  • E. TKK
    TKK is the former Helsinki University of Technology, a major Finnish institution known for its engineering and technology education and research.
  • 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: TKU
Triple: [Turku Airport, IATAcode, TKU]
Generated description
TKU is the IATA airport code for Turku Airport, a regional international airport serving the city of Turku in southwestern Finland.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: TKU
Target entity description: TKU is the IATA airport code for Turku Airport, a regional international airport serving the city of Turku in southwestern Finland.
  • A. KNTU
    KNTU is the ICAO airport code for Naval Air Station Oceana, a major United States Navy jet base located in Virginia Beach, Virginia.
  • B. TUKE
    TUKE is a major Slovak technical university based in Košice, known for its engineering, technology, and applied science programs.
  • C. KTUL
    KTUL is the ICAO airport code for Tulsa International Airport, a major commercial and military aviation facility serving Tulsa, Oklahoma.
  • D. TKK
    TKK is the IATA airport code for Chuuk International Airport, the main air gateway to Chuuk State in the Federated States of Micronesia.
  • E. TKK
    TKK is the former Helsinki University of Technology, a major Finnish institution known for its engineering and technology education and research.
  • 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_69d886da626481908a14ce7830329a35 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e42f4c209c81909c713ed78f2cb19a completed April 19, 2026, 1:26 a.m.
NED1 Entity disambiguation (via context triple) batch_6a01794d605481908b5e430c3142c203 completed May 11, 2026, 6:38 a.m.
NEDg Description generation batch_6a017b2642f8819084b339ea27ae1f84 completed May 11, 2026, 6:45 a.m.
NED2 Entity disambiguation (via description) batch_6a017c0e82c08190a37a36af68550c19 completed May 11, 2026, 6:49 a.m.
Created at: April 10, 2026, 5:40 a.m.