Triple
T25140940
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Drina Canyon |
E629799
|
entity |
| Predicate | riverFormsBoundaryBetween |
P31306
|
FINISHED |
| Object | Bosnia and Herzegovina |
—
|
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: Bosnia and Herzegovina | Statement: [Drina Canyon, riverFormsBoundaryBetween, Bosnia and Herzegovina]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: riverFormsBoundaryBetween Context triple: [Drina Canyon, riverFormsBoundaryBetween, Bosnia and Herzegovina]
-
A.
riverFormsBorderWith
chosen
Indicates that a river serves as a boundary line between two geographic or political entities.
-
B.
boundaryBetween
Indicates that something serves as a dividing line or limit separating two distinct regions, areas, or entities.
-
C.
stateBoundaryBetween
Indicates a boundary line that separates or lies between two states.
-
D.
watershedBetween
Indicates that a geographic feature or boundary serves as the dividing line between two drainage basins or river systems.
-
E.
fareBoundaryBetween
Indicates that there is a dividing line or zone where one fare region, zone, or pricing scheme ends and another begins.
- 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_69e2ff338250819096ff6c8892804389 |
completed | April 18, 2026, 3:49 a.m. |
| NER | Named-entity recognition | batch_69f497bc12b881908fe3386c66252bf6 |
completed | May 1, 2026, 12:08 p.m. |
| PD | Predicate disambiguation | batch_69f49366e8d08190adb4b71fe3a14683 |
completed | May 1, 2026, 11:49 a.m. |
Created at: April 18, 2026, 6:29 a.m.