Triple
T25096111
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 熊本市 |
E628592
|
entity |
| Predicate | 交通拠点 |
P36754
|
FINISHED |
| Object | 熊本空港へのアクセス拠点 |
—
|
LITERAL 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: 熊本空港へのアクセス拠点 | Statement: [熊本市, 交通拠点, 熊本空港へのアクセス拠点]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 交通拠点 Context triple: [熊本市, 交通拠点, 熊本空港へのアクセス拠点]
-
A.
transportationFacility
Indicates that one entity is a facility or location used for the transportation or transit of people or goods in relation to another entity.
-
B.
transportationJunctionFor
chosen
Indicates a location that serves as a connecting point where multiple transportation routes or modes meet, intersect, or transfer.
-
C.
transportationHubType
Indicates the specific kind of transportation hub an entity is (e.g., airport, train station, bus terminal).
-
D.
roadNetworkHubOf
Indicates that one location functions as a central node or hub within the road network relative to another location or area.
-
E.
roadTerminusOf
Indicates that a road ends at, or has its terminal point at, the referenced location or route.
- F. None of above.
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_69e2ff2f58e881908340527bc5d34f07 |
completed | April 18, 2026, 3:49 a.m. |
| NER | Named-entity recognition | batch_69f464b9651481908d4d7584717f5c59 |
completed | May 1, 2026, 8:30 a.m. |
| PD | Predicate disambiguation | batch_69f44d8043b081908bbffd7f044b4f26 |
completed | May 1, 2026, 6:51 a.m. |
Created at: April 18, 2026, 6:25 a.m.