Triple
T6220844
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Garang |
E139107
|
entity |
| Predicate | ethnicity |
P194
|
FINISHED |
| Object | Dinka |
E175971
|
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: Dinka | Statement: [John Garang, ethnicity, Dinka]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dinka Context triple: [John Garang, ethnicity, Dinka]
-
A.
Dinka
chosen
Dinka is a Nilotic language spoken primarily by the Dinka people of South Sudan.
-
B.
Tekeze River
The Tekeze River is a major river in the Horn of Africa that flows through northern Ethiopia and Eritrea, carving one of the deepest gorges in Africa before joining the Atbarah River.
-
C.
Hadejia
Hadejia is a historic commercial and agricultural town in northeastern Nigeria, known for its emirate, river basin, and role as a key urban center in Jigawa State.
-
D.
Anseba River
The Anseba River is a major seasonal watercourse in Eritrea that flows from the central highlands toward the Red Sea basin, supporting agriculture and settlements along its valley.
-
E.
Tuma River
The Tuma River is a significant waterway in Nicaragua that serves as a major tributary feeding the country’s largest freshwater body, Gran Lago (Lake Nicaragua).
- 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_69c008aecb0c81909984b48f733ce8ae |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c062bcc2348190806ed8c98bdfbf3e |
completed | March 22, 2026, 9:44 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c603e5b3d48190b156be02008a8c12 |
completed | March 27, 2026, 4:13 a.m. |
Created at: March 22, 2026, 4:21 p.m.