Triple
T10665809
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Almaty International Airport |
E251354
|
entity |
| Predicate | focusCityFor |
P164
|
FINISHED |
| Object | Qazaq Air |
E857605
|
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: Qazaq Air | Statement: [Almaty International Airport, focusCityFor, Qazaq Air]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Qazaq Air Context triple: [Almaty International Airport, focusCityFor, Qazaq Air]
-
A.
Qazaq Air
chosen
Qazaq Air is a regional airline of Kazakhstan that operates domestic routes connecting major cities and remote regions across the country.
-
B.
Air Astana
Air Astana is the flag carrier airline of Kazakhstan, operating domestic and international flights primarily from its main bases in Astana and Almaty.
-
C.
Angara Airlines
Angara Airlines is a Russian regional airline based in Siberia that operates passenger and cargo flights, primarily serving destinations across eastern Russia.
-
D.
Alia Airlines
Alia Airlines was the original name of Royal Jordanian, the flag carrier airline of Jordan.
-
E.
Siberia Airlines
Siberia Airlines, now known as S7 Airlines, is a major Russian airline that operates domestic and international flights with a primary hub in Novosibirsk.
- 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_69d6aa5b0d2881909584b20efc5877f0 |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d6f31f87748190bb44db8afa901763 |
completed | April 9, 2026, 12:30 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d9885dc17881909df20abedd9da5e3 |
completed | April 10, 2026, 11:31 p.m. |
Created at: April 8, 2026, 9:08 p.m.