Triple
T26698972
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South China Sea maritime claims |
E673099
|
entity |
| Predicate | involvesExternalPower |
P176704
|
FINISHED |
| Object | United States |
—
|
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: United States | Statement: [South China Sea maritime claims, involvesExternalPower, United States]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: involvesExternalPower Context triple: [South China Sea maritime claims, involvesExternalPower, United States]
-
A.
involvesPower
Indicates that the relationship or action includes the use, exercise, transfer, or influence of power or authority between the entities involved.
-
B.
hasPowerSource
Indicates that an entity derives its operational energy or functionality from a specified power source.
-
C.
hasPowerTerminal
Indicates that an entity is equipped with or connected to a power terminal through which electrical power can be supplied or distributed.
-
D.
involvesPowerType
Indicates that the relationship or action is associated with, characterized by, or dependent on a specific type or category of power.
-
E.
hasPowerSupplyType
Indicates that an entity is associated with a specific type or category of power supply it uses or requires.
- F. None of above. chosen
Provenance (4 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_69eecda2b49c8190a6c481cfc4c07954 |
completed | April 27, 2026, 2:44 a.m. |
| NER | Named-entity recognition | batch_69f6e6029a10819098ff21f58079e70e |
completed | May 3, 2026, 6:06 a.m. |
| PD | Predicate disambiguation | batch_69f6e3d5e8188190b1e1c2e5d1b77031 |
completed | May 3, 2026, 5:57 a.m. |
| PDg | Predicate description generation | batch_69f6e60109648190947a64ca4ce81a3a |
completed | May 3, 2026, 6:06 a.m. |
Created at: April 27, 2026, 3:30 a.m.