Triple
T20753369
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aloha Airlines |
E510787
|
entity |
| Predicate | operatedDestination |
P50377
|
FINISHED |
| Object | Kona |
—
|
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: Kona | Statement: [Aloha Airlines, operatedDestination, Kona]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kona Context triple: [Aloha Airlines, operatedDestination, Kona]
-
A.
Kona
Kona is a locality in the Howrah district of West Bengal, India, known for its strategic position near major transport routes connecting to Kolkata.
-
B.
Kona
chosen
Kona is a coastal town on the western side of Hawaii's Big Island, known for its coffee farms, historic sites, and popular snorkeling and diving spots.
-
C.
Koa
Koa is a lightweight, modern Node.js web framework designed by the creators of Express to provide a more expressive and robust foundation for web applications and APIs.
-
D.
Kaʻala
Kaʻala is the Hawaiian name for Mount Kaʻala, the highest peak on the island of Oʻahu.
-
E.
Kimo
Kimo is a retired American mixed martial artist and kickboxer best known for his early UFC appearances and his distinctive, heavily tattooed persona.
- 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_69e0b4c909ec8190b05987f1639513f6 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c22d0ebc8190b17077326f540f98 |
completed | April 21, 2026, 12:17 a.m. |
Created at: April 16, 2026, 12:34 p.m.