Triple
T26714924
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bosnia and Herzegovina–Montenegro border |
E673523
|
entity |
| Predicate | passesAlongEntity |
P67932
|
FINISHED |
| Object | Drina River |
—
|
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: Drina River | Statement: [Bosnia and Herzegovina–Montenegro border, passesAlongEntity, Drina River]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: passesAlongEntity Context triple: [Bosnia and Herzegovina–Montenegro border, passesAlongEntity, Drina River]
-
A.
passedAlongside
chosen
Indicates that one entity moved or traveled next to another entity along the same route or path, maintaining a roughly parallel course.
-
B.
passesFeature
Indicates that one entity successfully satisfies, verifies, or meets the criteria of a specified feature or test condition associated with another entity.
-
C.
flowsThroughEntity
Indicates that a substance, medium, or influence moves along a path that passes through the referenced entity.
-
D.
isPassedThroughBy
Indicates that something serves as a medium, route, or channel through which another thing moves, flows, or is transmitted.
-
E.
passesThroughArea
Indicates that an entity moves or extends through the spatial region defined by 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_69eecda3a22881908f3061c760b9d542 |
completed | April 27, 2026, 2:44 a.m. |
| NER | Named-entity recognition | batch_69f657f653448190a945b4751af8507d |
completed | May 2, 2026, 8 p.m. |
| PD | Predicate disambiguation | batch_69f6575ba12081909396036f78757a76 |
completed | May 2, 2026, 7:58 p.m. |
Created at: April 27, 2026, 3:37 a.m.