Triple
T37600681
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zhongsha Islands |
E935513
|
entity |
| Predicate | disputedRegionOf |
P15542
|
FINISHED |
| Object | South China Sea |
—
|
NE NERFINISHED |
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: South China Sea | Statement: [Zhongsha Islands, disputedRegionOf, South China Sea]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: disputedRegionOf Context triple: [Zhongsha Islands, disputedRegionOf, South China Sea]
-
A.
locatedInDisputedTerritory
chosen
Indicates that an entity is situated within a geographic area whose sovereignty or ownership is contested between two or more parties.
-
B.
associatedTerritoryDispute
Indicates that there is a territorial dispute or contested claim connected to the referenced entity or relationship.
-
C.
conflictRegion
Indicates that the entities are located in or associated with a geographic area characterized by active or recent conflict, tension, or hostilities.
-
D.
countryContestedBy
Indicates that control, ownership, or sovereignty over a country is disputed by multiple parties or entities.
-
E.
hasDisputedMaritimeBoundary
Indicates that there is an unresolved or contested maritime boundary claim between two or more 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_69f76ecf39c081909baffe597bb55273 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fbacaf54648190811ea33b34907e8e |
completed | May 6, 2026, 9:03 p.m. |
| PD | Predicate disambiguation | batch_69fba883f770819091059c6f6c6af9f7 |
completed | May 6, 2026, 8:45 p.m. |
Created at: May 3, 2026, 4:18 p.m.