Triple
T27043519
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gunsan Airport |
E684556
|
entity |
| Predicate | supportsCivilianOperations |
P173640
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [Gunsan Airport, supportsCivilianOperations, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsCivilianOperations Context triple: [Gunsan Airport, supportsCivilianOperations, true]
-
A.
supportsCivilAuthorities
Indicates that one entity provides assistance, endorsement, or backing to civil authorities in performing their roles or exercising their powers.
-
B.
allowsCivilianService
Indicates that an authority permits individuals to perform an alternative form of civilian service instead of regular military service.
-
C.
militarySupportActivity
Indicates an action where one entity provides military-related assistance, resources, or operational support to another.
-
D.
supportsMedEvacOperations
Indicates the capability or role of providing assistance, resources, or infrastructure necessary to conduct medical evacuation operations.
-
E.
isCivilianBased
chosen
Indicates that something is primarily oriented toward, derived from, or operating within a civilian (non-military) context.
- 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_69ef148193c48190bb1a0cfae6a407c4 |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69fedd5a5f4c8190acce88db56303703 |
completed | May 9, 2026, 7:08 a.m. |
| PD | Predicate disambiguation | batch_69fed910b31c8190ae837163d146738d |
completed | May 9, 2026, 6:49 a.m. |
Created at: April 27, 2026, 8:07 a.m.