Triple
T12213015
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gaven Reefs |
E291010
|
entity |
| Predicate | relevantIssue |
P29037
|
FINISHED |
| Object | status as rocks, islands, or low-tide elevations under UNCLOS |
—
|
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: status as rocks, islands, or low-tide elevations under UNCLOS | Statement: [Gaven Reefs, relevantIssue, status as rocks, islands, or low-tide elevations under UNCLOS]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relevantIssue Context triple: [Gaven Reefs, relevantIssue, status as rocks, islands, or low-tide elevations under UNCLOS]
-
A.
involvesIssue
chosen
Indicates that an action, event, or entity is related to, concerns, or includes a particular issue.
-
B.
underlyingIssue
Indicates that one situation, problem, or condition is the fundamental cause or root problem behind another.
-
C.
possibleIssue
Indicates that there is a potential or suspected problem, defect, or undesired condition associated with the referenced entity or situation, though it is not yet confirmed.
-
D.
raisedConcernAbout
Indicates that one entity has expressed worry, doubt, or objection regarding another entity or issue.
-
E.
knownIssue
Indicates that the subject has an issue or problem that is already identified, recognized, or documented.
- 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_69d6ab65923081909acfc61b7a612233 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d920e312708190b4aede2e21f5f697 |
completed | April 10, 2026, 4:10 p.m. |
| PD | Predicate disambiguation | batch_69d91c3d669c81908eea7ad61122d275 |
completed | April 10, 2026, 3:50 p.m. |
Created at: April 8, 2026, 9:51 p.m.