Triple
T6220827
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dinka people |
E139107
|
entity |
| Predicate | subgroup |
P10
|
FINISHED |
| Object | Rek Dinka |
E323725
|
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: Rek Dinka | Statement: [Dinka people, subgroup, Rek Dinka]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rek Dinka Context triple: [Dinka people, subgroup, Rek Dinka]
-
A.
Jikany Nuer
Jikany Nuer is a dialect of the Nuer language spoken by the Jikany subgroup of the Nuer people in South Sudan and neighboring regions.
-
B.
Bul Nuer
Bul Nuer is a dialect of the Nuer language spoken by a subgroup of the Nuer people in South Sudan and neighboring regions.
-
C.
Dinka
Dinka is a Nilotic language spoken primarily by the Dinka people of South Sudan.
-
D.
Dok Nuer
Dok Nuer is a dialect of the Nuer language spoken by a subgroup of the Nuer people in South Sudan and neighboring regions.
-
E.
Agar Dinka
chosen
Agar Dinka is a dialect of the Dinka language spoken by the Agar subgroup of the Dinka people in South 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_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_69c243f042b08190a32bb07acd419b4c |
completed | March 24, 2026, 7:57 a.m. |
Created at: March 22, 2026, 4:21 p.m.