Triple
T25732594
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ghojadanga |
E645282
|
entity |
| Predicate | borderStateOnIndianSide |
P85007
|
FINISHED |
| Object | West Bengal |
—
|
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: West Bengal | Statement: [Ghojadanga, borderStateOnIndianSide, West Bengal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: borderStateOnIndianSide Context triple: [Ghojadanga, borderStateOnIndianSide, West Bengal]
-
A.
hasBorderTownOnIndianSide
Indicates that a location has a corresponding town situated on the Indian side of an international border.
-
B.
borderingIndianStates
chosen
Indicates that one or more Indian states share a common land or maritime boundary with a given geographic or political entity.
-
C.
borderStateOnUSSide
Indicates that a state is located on the U.S. side of an international border shared with another country.
-
D.
borderingUnionTerritory
Indicates that one entity shares a land or maritime boundary with a specified Union Territory.
-
E.
borderStateOf
Indicates that one state shares a common boundary or border with another state.
- 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_69e77e85254081908d79ee4e8715f283 |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f66c5c13808190887180099745673b |
completed | May 2, 2026, 9:27 p.m. |
| PD | Predicate disambiguation | batch_69f66abddc448190a488852f8abdeb2c |
completed | May 2, 2026, 9:21 p.m. |
Created at: April 21, 2026, 11:18 p.m.