Triple
T105743
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | East China Sea |
E2132
|
entity |
| Predicate | hasDispute |
P2693
|
FINISHED |
| Object | maritime boundary disputes between China and Japan |
—
|
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: maritime boundary disputes between China and Japan | Statement: [East China Sea, hasDispute, maritime boundary disputes between China and Japan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDispute Context triple: [East China Sea, hasDispute, maritime boundary disputes between China and Japan]
-
A.
hasDisputeHistory
Indicates that there has been at least one prior dispute or conflict involving the related entities.
-
B.
statusDisputedBy
Indicates that the validity, accuracy, or recognition of a status is being challenged or contested by a specified party.
-
C.
disputePolicy
Indicates that there is a formal disagreement or conflict regarding a policy, typically triggering procedures for review, negotiation, or resolution.
-
D.
contestedBy
chosen
Indicates that one party challenges, disputes, or opposes a claim, decision, or position held by another party.
-
E.
endedConflict
Indicates that a previously ongoing conflict between entities has been brought to an end.
- 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_69a24e0a5b7c81908d52da08c60dabc4 |
completed | Feb. 28, 2026, 2:08 a.m. |
| NER | Named-entity recognition | batch_69a256ec650c8190bee2067e37065527 |
completed | Feb. 28, 2026, 2:46 a.m. |
| PD | Predicate disambiguation | batch_69a2563d33788190999d471b486d5603 |
completed | Feb. 28, 2026, 2:43 a.m. |
Created at: Feb. 28, 2026, 2:12 a.m.