Triple
T12155166
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Berom |
E289554
|
entity |
| Predicate | hasDialects |
P4251
|
FINISHED |
| Object | Ropp dialect |
E341607
|
NE FINISHED |
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: Ropp dialect | Statement: [Berom, hasDialects, Ropp dialect]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ropp dialect Context triple: [Berom, hasDialects, Ropp dialect]
-
A.
Ropp dialect
chosen
Ropp dialect is a regional variety of the Berom language spoken in and around the Ropp area of Plateau State, Nigeria.
-
B.
Rumbur dialect
The Rumbur dialect is a regional variety of the Kalasha language spoken in the Rumbur Valley of northern Pakistan.
-
C.
Aknogai dialect
The Aknogai dialect is a regional variety of the Nogai language spoken by Nogai communities in the North Caucasus.
-
D.
Deogrom dialect
The Deogrom dialect is a regional variety of the Prasuni language spoken by a specific community in the Deogrom area.
-
E.
Tappalang dialect
The Tappalang dialect is a regional variety of the Mandar language spoken by Mandar communities in parts of West Sulawesi, Indonesia.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d6ab4c6710819097a9d228382dde43 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d915c1673c8190830cd15525d16869 |
completed | April 10, 2026, 3:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f5f69c8d408190abbc900deb534045 |
completed | May 2, 2026, 1:05 p.m. |
Created at: April 8, 2026, 9:50 p.m.