Triple

T2628556
Position Surface form Disambiguated ID Type / Status
Subject Kauhava Air Base E59178 entity
Predicate IATACode P418 FINISHED
Object KAU
KAU is the IATA airport code for Kauhava Air Base, a former military airfield in Kauhava, Finland.
 E284551 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: KAU | Statement: [Kauhava Air Base, IATACode, KAU]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: KAU
Context triple: [Kauhava Air Base, IATACode, KAU]
  • A. KAUG
    KAUG is the ICAO airport code for Augusta State Airport, a public airport serving Augusta, Maine, in the United States.
  • B. KA
    KA is the vehicle registration code used on license plates for cars registered in the German city of Karlsruhe.
  • C. 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.
  • D. KUO
    KUO is the IATA airport code for Kuopio Airport in Finland.
  • E. Ka
    Ka was an early ancient Egyptian king of the First Dynasty period, known from tomb inscriptions at Abydos and considered one of the first rulers to use a royal serekh.
  • 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: KAU
Triple: [Kauhava Air Base, IATACode, KAU]
Generated description
KAU is the IATA airport code for Kauhava Air Base, a former military airfield in Kauhava, Finland.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: KAU
Target entity description: KAU is the IATA airport code for Kauhava Air Base, a former military airfield in Kauhava, Finland.
  • A. KAUG
    KAUG is the ICAO airport code for Augusta State Airport, a public airport serving Augusta, Maine, in the United States.
  • B. KA
    KA is the vehicle registration code used on license plates for cars registered in the German city of Karlsruhe.
  • C. 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.
  • D. KUO
    KUO is the IATA airport code for Kuopio Airport in Finland.
  • E. Ka
    Ka was an early ancient Egyptian king of the First Dynasty period, known from tomb inscriptions at Abydos and considered one of the first rulers to use a royal serekh.
  • 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_69ab4ac558388190962492cd2e1b0ce6 completed March 6, 2026, 9:44 p.m.
NER Named-entity recognition batch_69abd8c2e3d88190a972f58356f282cc completed March 7, 2026, 7:50 a.m.
NED1 Entity disambiguation (via context triple) batch_69af90a44a348190b8b49b37418dd94b completed March 10, 2026, 3:31 a.m.
NEDg Description generation batch_69af9172ba248190bbc68a00b43d9b44 completed March 10, 2026, 3:35 a.m.
NED2 Entity disambiguation (via description) batch_69af92500920819082c651f75a06dd72 completed March 10, 2026, 3:38 a.m.
Created at: March 6, 2026, 9:50 p.m.