Triple
T21677613
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Southwest Air Lines |
E535014
|
entity |
| Predicate | primaryHub |
P394
|
FINISHED |
| Object | Naha Airport |
—
|
NE NERFINISHED |
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: Naha Airport | Statement: [Southwest Air Lines, primaryHub, Naha Airport]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Naha Airport Context triple: [Southwest Air Lines, primaryHub, Naha Airport]
-
A.
Naha Airport
chosen
Naha Airport is the main commercial airport serving Okinawa Prefecture in Japan, acting as a key domestic and regional hub in the Ryukyu Islands.
-
B.
Miyazaki Bougainvillea Airport
Miyazaki Bougainvillea Airport is a regional airport in Miyazaki Prefecture, Japan, serving domestic flights and limited international routes for the city of Miyazaki on Kyushu Island.
-
C.
Hana Airport
Hana Airport is a small regional airport serving the remote town of Hāna on the eastern coast of Maui, Hawaii.
-
D.
Yei Airport
Yei Airport is a small public airstrip serving the town of Yei in South Sudan, primarily handling domestic and regional flights.
-
E.
Susuman Airport
Susuman Airport is a small regional airport serving the town of Susuman in Magadan Oblast, Russia, providing air transport links to this remote area of the Russian Far East.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c46898008190aa618a4af55bd1ee |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef8a11088081908911af2629f54c1c |
completed | April 27, 2026, 4:08 p.m. |
Created at: April 16, 2026, 6:42 p.m.