Triple
T7389041
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Air Busan |
E170452
|
entity |
| Predicate | callsign |
P1565
|
FINISHED |
| Object | AIR BUSAN |
E170452
|
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: AIR BUSAN | Statement: [Air Busan, callsign, AIR BUSAN]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: AIR BUSAN Context triple: [Air Busan, callsign, AIR BUSAN]
-
A.
Air Seoul
Air Seoul is a South Korean low-cost airline based in Seoul that operates regional flights across East Asia.
-
B.
Air Busan
chosen
Air Busan is a South Korean low-cost airline based in Busan that operates domestic and international flights across East Asia.
-
C.
Akasa Air
Akasa Air is an Indian low-cost airline that began operations in 2022, offering domestic flights with a focus on affordable fares and a modern fleet.
-
D.
Jeju Air
Jeju Air is a South Korean low-cost airline that operates extensive domestic and international routes, particularly serving leisure and regional markets in East Asia.
-
E.
KAI Commuter
KAI Commuter is an Indonesian railway company that operates commuter rail services in the Greater Jakarta area and surrounding regions.
- 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_69c68a5e2c9081909e713ce866e0060a |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f1f512d881908056bdb88a58bea4 |
completed | March 27, 2026, 9:09 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c802e71bfc8190b45eb951c0311fce |
completed | March 28, 2026, 4:33 p.m. |
Created at: March 27, 2026, 3:09 p.m.