Triple
T33542500
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sadamisaki Peninsula |
E859108
|
entity |
| Predicate | hasNearbyPrefectureAcrossSea |
P197837
|
FINISHED |
| Object | Oita Prefecture |
—
|
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: Oita Prefecture | Statement: [Sadamisaki Peninsula, hasNearbyPrefectureAcrossSea, Oita Prefecture]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNearbyPrefectureAcrossSea Context triple: [Sadamisaki Peninsula, hasNearbyPrefectureAcrossSea, Oita Prefecture]
-
A.
hasNearbyPrefecture
Indicates that one administrative region has another prefecture located geographically close to it.
-
B.
nearbyRegionAcrossSea
chosen
Indicates that one region is geographically close to another, with a sea lying between them.
-
C.
hasNearbyProvince
Indicates that one province is geographically close to or directly adjacent to another province.
-
D.
neighboringIsland
Indicates that one island is geographically adjacent to or very close to another island, typically separated only by a narrow body of water.
-
E.
isCoastalPrefectureLevelCity
Indicates that a prefecture-level city is located along a sea or ocean coastline.
- 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_69f3497a5be08190a39b12736899e034 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69ff7eb7189c81909a8f73fbc4c48e02 |
completed | May 9, 2026, 6:36 p.m. |
| PD | Predicate disambiguation | batch_69ff7e54e11081908fb5ce10c5aa7b53 |
completed | May 9, 2026, 6:35 p.m. |
Created at: May 1, 2026, 1:39 a.m.