Triple
T18183193
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ulchi civil defense exercise of South Korea |
E435341
|
entity |
| Predicate | typeOfScenario |
P55686
|
FINISHED |
| Object | wartime emergency |
—
|
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: wartime emergency | Statement: [Ulchi civil defense exercise of South Korea, typeOfScenario, wartime emergency]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfScenario Context triple: [Ulchi civil defense exercise of South Korea, typeOfScenario, wartime emergency]
-
A.
scenarioType
chosen
Indicates the specific category or kind of situation, context, or use case that an entity or event is associated with.
-
B.
situationType
Indicates the general kind or category of situation, event, or circumstance that a given instance represents.
-
C.
variantScenario
Indicates a scenario that represents an alternative, modified, or derived version of another base scenario.
-
D.
performedInSceneType
Indicates that an action or event was carried out within a scene of a specified type or category.
-
E.
narrativeSituation
Indicates the contextual relationship that defines how events, characters, and perspectives are arranged and presented within a narrative.
- 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_69d8b90c7ec081909b4694ccecb449c6 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4dffc432c8190af53da5256dc476c |
completed | April 19, 2026, 2 p.m. |
| PD | Predicate disambiguation | batch_69e4331e92408190ad607ba4956a3897 |
completed | April 19, 2026, 1:42 a.m. |
Created at: April 10, 2026, 10:31 a.m.