Triple
T28830766
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roseires Hydropower Plant |
E728041
|
entity |
| Predicate | affectsDownstreamCountry |
P8692
|
FINISHED |
| Object | Sudan |
—
|
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: Sudan | Statement: [Roseires Hydropower Plant, affectsDownstreamCountry, Sudan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: affectsDownstreamCountry Context triple: [Roseires Hydropower Plant, affectsDownstreamCountry, Sudan]
-
A.
downstreamCountry
Indicates that one country is located downstream along a shared river or watercourse relative to another country.
-
B.
affectedCountry
chosen
Indicates that a particular country is impacted or influenced by an event, action, or condition.
-
C.
hasUpstreamImpactOn
Indicates that one entity’s actions, changes, or outputs affect another entity that is positioned earlier in a process, flow, or dependency chain.
-
D.
endingCountry
Indicates the country in which an event, journey, process, or relationship comes to an end.
-
E.
benefitedCountry
Indicates that one country gains an advantage, profit, or positive outcome from an action, event, or entity associated with another.
- 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_69f0319dc6088190bbfaa206d40ed74a |
completed | April 28, 2026, 4:03 a.m. |
| NER | Named-entity recognition | batch_69f6b903538481909cffcb6cc1cc0e70 |
completed | May 3, 2026, 2:54 a.m. |
| PD | Predicate disambiguation | batch_69f6b626120c819097c9ad04487570d7 |
completed | May 3, 2026, 2:42 a.m. |
Created at: April 28, 2026, 6:37 a.m.