Triple
T3055450
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dinka language |
E60468
|
entity |
| Predicate | region |
P40
|
FINISHED |
| Object | Bahr el Ghazal |
E262129
|
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: Bahr el Ghazal | Statement: [Dinka language, region, Bahr el Ghazal]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bahr el Ghazal Context triple: [Dinka language, region, Bahr el Ghazal]
-
A.
Bahr el Ghazal
chosen
Bahr el Ghazal is a major river and region in South Sudan that forms one of the principal western tributary systems of the White Nile.
-
B.
Central Sudan
Central Sudan is a historical region in north-central Africa encompassing parts of modern-day northern Nigeria and surrounding areas, known for its precolonial emirates and trans-Saharan trade networks.
-
C.
Ennedi
Ennedi is a remote region in northeastern Chad renowned for its dramatic sandstone massifs, rock arches, and prehistoric rock art.
-
D.
Arabi Juba
Arabi Juba is a colloquial Arabic-based creole widely spoken as a lingua franca in and around Juba, South Sudan.
-
E.
Kenuzi-Dongola
Kenuzi-Dongola is a Nubian language of the Eastern Sudanic branch spoken primarily along the Nile in southern Egypt and northern Sudan.
- 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_69ad8578137c81908259dcb27c7d6d7c |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ad9bf6b9948190bc957bfd1579c471 |
completed | March 8, 2026, 3:55 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b1ef03425c8190a44486ab563c210f |
completed | March 11, 2026, 10:38 p.m. |
Created at: March 8, 2026, 3:02 p.m.