Triple
T16124912
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pungwe River |
E391242
|
entity |
| Predicate | hasTransboundaryBasin |
P66357
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [Pungwe River, hasTransboundaryBasin, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTransboundaryBasin Context triple: [Pungwe River, hasTransboundaryBasin, true]
-
A.
transboundaryBasin
chosen
Indicates that a river basin or watershed extends across and is shared by the territories of two or more political or administrative jurisdictions.
-
B.
transboundaryRiverOf
Indicates that a river crosses or forms the boundary between two or more political or administrative regions.
-
C.
hasHydrologicalBoundary
Indicates that one entity serves as a hydrological boundary or limit for another, typically defining the extent of a water-related area or system.
-
D.
transboundaryWaterManagement
Indicates the cooperative planning, regulation, and use of shared water resources that cross political or administrative boundaries between different jurisdictions.
-
E.
isTransboundaryVolcano
Indicates that a volcano spans or affects the territories of more than one country or jurisdiction.
- 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_69d87f1bb0988190b490d273dbf3fd03 |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e2020408a88190bf3dfc893d577c55 |
completed | April 17, 2026, 9:48 a.m. |
| PD | Predicate disambiguation | batch_69e1828518c48190a8ef3aaa46a1f639 |
completed | April 17, 2026, 12:44 a.m. |
Created at: April 10, 2026, 5 a.m.