Triple

T15658414
Position Surface form Disambiguated ID Type / Status
Subject Kamloops Airport E376506 entity
Predicate ICAO code P419 FINISHED
Object CYKA E1170298 NE FINISHED

How this triple was built (2 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: CYKA | Statement: [Kamloops Airport, ICAO code, CYKA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: CYKA
Context triple: [Kamloops Airport, ICAO code, CYKA]
  • A. CYKA chosen
    CYKA is the ICAO airport code for Kamloops Airport, a regional airport serving the city of Kamloops in British Columbia, Canada.
  • B. KYA
    KYA is the IATA airport code for Konya Airport, a public and military airport serving the city of Konya in Turkey.
  • C. CYMX
    CYMX is the ICAO airport code for Montréal–Mirabel International Airport, a major cargo and aerospace hub located northwest of Montreal, Quebec, Canada.
  • D. YKA
    YKA is the IATA airport code for Kamloops Airport, a regional airport serving the city of Kamloops in British Columbia, Canada.
  • E. CYKG
    CYKG is the ICAO airport code assigned to Kangiqsujuaq Airport in Quebec, Canada.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d85cd1564c8190991adda63bfab4b0 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04ef3cb8c8190a10815b675b341c1 completed April 16, 2026, 2:52 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff6ed6f50c81909d87ced263064f0d completed May 9, 2026, 5:28 p.m.
Created at: April 10, 2026, 4:15 a.m.