Triple
T4184189
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Auckland Airport |
E88269
|
entity |
| Predicate | servesAirline |
P12356
|
FINISHED |
| Object | Korean Air |
E30717
|
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: Korean Air | Statement: [Auckland Airport, servesAirline, Korean Air]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Korean Air Context triple: [Auckland Airport, servesAirline, Korean Air]
-
A.
Korean Air
chosen
Korean Air is South Korea’s largest airline and flag carrier, operating extensive international and domestic passenger and cargo services worldwide.
-
B.
Asiana Airlines
Asiana Airlines is a major South Korean international airline based in Seoul, operating an extensive network of passenger and cargo services across Asia, Europe, North America, and Oceania.
-
C.
Jin Air
Jin Air is a South Korean low-cost airline that operates domestic and international passenger flights.
-
D.
Asia Pacific Airlines
Asia Pacific Airlines is a cargo and charter airline based in Guam that primarily serves destinations across Micronesia and the Western Pacific region.
-
E.
Skymark Airlines
Skymark Airlines is a Japanese low-cost carrier based in Tokyo that operates domestic flights and some international services.
- 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_69aed9477e8c81908bcb862d2db55b1d |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69af0321eee88190871c1d4bf44a5007 |
completed | March 9, 2026, 5:28 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b589fe4b508190a1c5a1d426245ede |
completed | March 14, 2026, 4:17 p.m. |
Created at: March 9, 2026, 3:45 p.m.