Triple
T26058191
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Montenegro–Albania border |
E657182
|
entity |
| Predicate | nearbyCityAlbania |
P172763
|
FINISHED |
| Object | Shkodër |
—
|
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: Shkodër | Statement: [Montenegro–Albania border, nearbyCityAlbania, Shkodër]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: nearbyCityAlbania Context triple: [Montenegro–Albania border, nearbyCityAlbania, Shkodër]
-
A.
nearCityInNorthMacedonia
Indicates that one entity is located close to a specified city within the country of North Macedonia.
-
B.
nearestTownSerbia
Indicates the relationship where a given location is associated with the geographically closest town within the territory of Serbia.
-
C.
distanceToTirana_km
Indicates the physical distance, measured in kilometers, between a given place and the city of Tirana.
-
D.
distanceToKorçë
Indicates the spatial distance between an entity and the location of Korçë.
-
E.
nearestForeignCity
Indicates that one city is the geographically closest city located in a different country relative to another city.
- F. None of above. chosen
Provenance (4 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_69ee5bbd788481909e22bd7153d0c037 |
completed | April 26, 2026, 6:38 p.m. |
| NER | Named-entity recognition | batch_69f6b0d21dd08190a9883ff71c94c71c |
completed | May 3, 2026, 2:20 a.m. |
| PD | Predicate disambiguation | batch_69f6aca204148190850a3dc325bc07b7 |
completed | May 3, 2026, 2:02 a.m. |
| PDg | Predicate description generation | batch_69f6afeaaef88190aefa97e83f8db906 |
completed | May 3, 2026, 2:16 a.m. |
Created at: April 26, 2026, 7:13 p.m.