Triple
T27305804
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Myanmar–Bangladesh border |
E689052
|
entity |
| Predicate | hasBorderDivision |
P224
|
FINISHED |
| Object | Chittagong Division |
—
|
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: Chittagong Division | Statement: [Myanmar–Bangladesh border, hasBorderDivision, Chittagong Division]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasBorderDivision Context triple: [Myanmar–Bangladesh border, hasBorderDivision, Chittagong Division]
-
A.
hasBorderingSubdivision
Indicates that one subdivision directly borders or shares a boundary with another subdivision.
-
B.
bordersInternalDivision
Indicates that one administrative or internal division shares a common boundary with another internal division within the same larger entity.
-
C.
isBorderDistrict
Indicates that a district is located along and directly borders the boundary of a larger administrative region or country.
-
D.
borderedBy
chosen
Indicates that one entity shares a common boundary or edge with another entity.
-
E.
isDividedByModernBorder
Indicates that a single entity or area is split into separate parts by a contemporary political or administrative boundary.
- 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_69ef355b931c8190a63cafaf7bcc008b |
completed | April 27, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69f6e6029a10819098ff21f58079e70e |
completed | May 3, 2026, 6:06 a.m. |
| PD | Predicate disambiguation | batch_69f6e3d5e8188190b1e1c2e5d1b77031 |
completed | May 3, 2026, 5:57 a.m. |
Created at: April 27, 2026, 11:24 a.m.