Triple
T30016846
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jaigaon–Phuentsholing border crossing |
E762618
|
entity |
| Predicate | locatedInTownOnBhutaneseSide |
P202443
|
FINISHED |
| Object | Phuentsholing |
—
|
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: Phuentsholing | Statement: [Jaigaon–Phuentsholing border crossing, locatedInTownOnBhutaneseSide, Phuentsholing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locatedInTownOnBhutaneseSide Context triple: [Jaigaon–Phuentsholing border crossing, locatedInTownOnBhutaneseSide, Phuentsholing]
-
A.
locatedInBorderDistrictOnNepaliSide
Indicates that something is situated within a border district that lies on the Nepali side of an international boundary.
-
B.
hasBorderTownOnNepaliSide
Indicates that a location has a corresponding town situated on the Nepali side of an international border.
-
C.
borderingBhutaneseDistricts
Indicates that the specified Bhutanese districts share a common boundary with each other.
-
D.
capitalDzongOf
Indicates that one entity is the administrative capital (dzong) of a specified region or district.
-
E.
borderStateOnNepalSide
Indicates that a state lies along and shares a border with Nepal, specifically on Nepal’s side of the boundary.
- 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_69f2246b0c84819094f1250b6a02d277 |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_6a008098e5dc8190b7ccad8bab780343 |
completed | May 10, 2026, 12:56 p.m. |
| PD | Predicate disambiguation | batch_6a008037267c8190990225a6ff0b3694 |
completed | May 10, 2026, 12:55 p.m. |
| PDg | Predicate description generation | batch_6a00809836f081908de40255d4f4d525 |
completed | May 10, 2026, 12:56 p.m. |
Created at: April 29, 2026, 6:46 p.m.