Triple
T23372019
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 松輪島 |
E593499
|
entity |
| Predicate | 軍事施設 |
P107809
|
FINISHED |
| Object | 飛行場が建設されたとされる |
—
|
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: 飛行場が建設されたとされる | Statement: [松輪島, 軍事施設, 飛行場が建設されたとされる]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 軍事施設 Context triple: [松輪島, 軍事施設, 飛行場が建設されたとされる]
-
A.
militaryInstallationType
Indicates the specific category or kind of military installation associated with an entity (e.g., base, fort, airfield, naval station).
-
B.
nearMilitaryInstallation
Indicates that one entity is located in close physical proximity to a military installation or facility.
-
C.
hostsMilitaryInstallation
Indicates that a location contains or accommodates a military base, facility, or installation operated by armed forces.
-
D.
isMilitaryInstallation
chosen
Indicates that a location functions as a military facility or base used for defense, training, operations, or related armed forces activities.
-
E.
militaryBasis
Indicates that one entity serves as the foundational military justification, rationale, or underlying military reason for another entity or action.
- 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_69e25d2593c88190bcdf4a716a94ccb2 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1a3af45ec8190a32aa4e5f04f6756 |
completed | April 29, 2026, 6:22 a.m. |
| PD | Predicate disambiguation | batch_69f061c7aaa48190a58ce93f87155ffc |
completed | April 28, 2026, 7:29 a.m. |
Created at: April 17, 2026, 5:32 p.m.