Triple
T5432698
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Second Battle of Yeonpyeong |
E121532
|
entity |
| Predicate | conflictPhase |
P28865
|
FINISHED |
| Object | post-1990s NLL naval clashes |
—
|
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: post-1990s NLL naval clashes | Statement: [Second Battle of Yeonpyeong, conflictPhase, post-1990s NLL naval clashes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: conflictPhase Context triple: [Second Battle of Yeonpyeong, conflictPhase, post-1990s NLL naval clashes]
-
A.
conflictPeriod
chosen
Indicates the time span during which a particular conflict or dispute is occurring or in effect between the related entities.
-
B.
conflictType
Indicates the specific kind or category of conflict that characterizes the relationship or interaction between entities.
-
C.
conflictIn
Indicates that one entity is involved in, associated with, or occurs within a particular conflict or dispute.
-
D.
conflictContext
Indicates the situational background or circumstances within which a conflict between entities occurs or is interpreted.
-
E.
conflictSpecific
Indicates a specific, concrete instance or type of conflict that exists between the related entities.
- 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_69bd463c65f0819082ee6483ab4b466a |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd8911a7348190ad9378a248190f07 |
completed | March 20, 2026, 5:51 p.m. |
| PD | Predicate disambiguation | batch_69bd846b8bdc81909dcdc2a3084226f2 |
completed | March 20, 2026, 5:31 p.m. |
Created at: March 20, 2026, 2:06 p.m.