Triple
T4203293
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kagoshima Airport |
E86120
|
entity |
| Predicate | connectsToIsland |
P27557
|
FINISHED |
| Object | Yakushima |
E444729
|
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: Yakushima | Statement: [Kagoshima Airport, connectsToIsland, Yakushima]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Yakushima Context triple: [Kagoshima Airport, connectsToIsland, Yakushima]
-
A.
Yakushima
chosen
Yakushima is a subtropical Japanese island renowned for its ancient cedar forests, rich biodiversity, and status as a UNESCO World Heritage Site.
-
B.
Yashima
Yashima is a historic plateau and former island in Takamatsu, Kagawa Prefecture, known for its panoramic views of the Seto Inland Sea and as a key battlefield of the Genpei War.
-
C.
Tokunoshima
Tokunoshima is a subtropical Japanese island in Kagoshima Prefecture known for its unique biodiversity, traditional culture, and role as part of the Amami archipelago.
-
D.
Kikaijima
Kikaijima is a small coral island in Japan’s Kagoshima Prefecture, known for its limestone plateau landscape, sugarcane cultivation, and location within the Amami archipelago.
-
E.
Rokkō Island
Rokkō Island is a large man-made island in Kobe, Japan, known for its residential areas, commercial facilities, and port-related infrastructure in Osaka Bay.
- 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_69aed93b89f48190a31f6d57c760e42f |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69af0b2db368819080c1d652b4acfd0c |
completed | March 9, 2026, 6:02 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bf7fbd0bc881908ba07edb75479b97 |
completed | March 22, 2026, 5:35 a.m. |
Created at: March 9, 2026, 3:49 p.m.