Triple
T33600966
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dnieper–Black Sea waterway |
E860718
|
entity |
| Predicate | linkedRiverBasin |
P72732
|
FINISHED |
| Object | Dnieper River basin |
—
|
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: Dnieper River basin | Statement: [Dnieper–Black Sea waterway, linkedRiverBasin, Dnieper River basin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: linkedRiverBasin Context triple: [Dnieper–Black Sea waterway, linkedRiverBasin, Dnieper River basin]
-
A.
associatedRiverBasin
chosen
Indicates that one entity is linked to, or lies within the drainage area of, a particular river basin.
-
B.
useRiverSystems
Indicates that an entity utilizes or manages river systems for a particular purpose or function.
-
C.
countryDownstreamBasin
Indicates that one country lies within the downstream portion of a river basin relative to another country or reference point.
-
D.
hasHeadwatersOf
Indicates that a specified location or feature is the source or origin point of a particular river or watercourse.
-
E.
resourceBasin
Indicates a relationship where a basin serves as a source or reservoir of resources for another entity or area.
- 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_69f3497f35908190a2e9bbb9b96c7a3f |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69fdd2be648c8190b60b3d1caeb44364 |
completed | May 8, 2026, 12:10 p.m. |
| PD | Predicate disambiguation | batch_69fdd14a5c708190a6f95ec61f4fc28f |
completed | May 8, 2026, 12:04 p.m. |
Created at: May 1, 2026, 1:41 a.m.