Triple
T12155421
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jos North Local Government Area |
E289560
|
entity |
| Predicate | languageUsed |
P238
|
FINISHED |
| Object | Berom (in parts) |
E289554
|
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: Berom (in parts) | Statement: [Jos North Local Government Area, languageUsed, Berom (in parts)]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Berom (in parts) Context triple: [Jos North Local Government Area, languageUsed, Berom (in parts)]
-
A.
Berom
chosen
Berom is a Plateau language spoken predominantly by the Berom people in and around Jos in central Nigeria.
-
B.
Bremthal
Bremthal is a district of the town of Eppstein in the state of Hesse, Germany, known as a residential community within the Rhine-Main metropolitan region.
-
C.
Lombe
Lombe is a city located in the Indonesian province of Southeast Sulawesi.
-
D.
Berd
Berd is a small historic town in northeastern Armenia known for its medieval fortresses and scenic location in Tavush Province near the border with Azerbaijan.
-
E.
Berendries
Berendries is a renowned, steep cobbled climb in the Flemish Ardennes of Belgium, frequently featured in professional cycling races such as the Tour of Flanders.
- 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.