Triple
T14153709
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ndiadiane Ndiaye |
E350754
|
entity |
| Predicate | title |
P38
|
FINISHED |
| Object | Buurba Jolof |
E350749
|
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: Buurba Jolof | Statement: [Ndiadiane Ndiaye, title, Buurba Jolof]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Buurba Jolof Context triple: [Ndiadiane Ndiaye, title, Buurba Jolof]
-
A.
Buurba Jolof
chosen
Buurba Jolof was the royal title borne by the kings who ruled the historic Wolof Empire in what is now Senegal.
-
B.
Jallow
Jallow is a common Gambian surname borne by various notable figures in West African public life, law, and politics.
-
C.
Badja Djola
Badja Djola was an American character actor known for his intense and memorable supporting roles in films and television from the 1970s through the 1990s.
-
D.
Wagadou
Wagadou is the historical name for the Ghana Empire, a powerful West African trading state that flourished between the 6th and 13th centuries.
-
E.
Langoué Baï
Langoué Baï is a renowned forest clearing in Gabon celebrated for its rich biodiversity and frequent gatherings of forest elephants and other wildlife.
- 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_69d8278775fc8190b0802d22ca2f495d |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de6133754881908e1e97db71772deb |
completed | April 14, 2026, 3:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd19395924819084d78815c3f12f43 |
completed | May 7, 2026, 10:59 p.m. |
Created at: April 10, 2026, 12:57 a.m.