Triple
T23368459
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Oroko |
E593391
|
entity |
| Predicate | region |
P40
|
FINISHED |
| Object | Fako Division |
—
|
NE NERFINISHED |
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: Fako Division | Statement: [Oroko, region, Fako Division]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fako Division Context triple: [Oroko, region, Fako Division]
-
A.
Fako Division
chosen
Fako Division is an administrative division in Cameroon’s Southwest Region that includes coastal towns such as Limbe and the slopes of Mount Cameroon.
-
B.
Koulamoutou
Koulamoutou is a town in central Gabon that serves as an administrative and economic hub for the surrounding region.
-
C.
Rumuokoro
Rumuokoro is a bustling urban town and major commercial transport hub in Obio-Akpor, within the Port Harcourt metropolitan area of Rivers State, Nigeria.
-
D.
Fako
Fako is an alternative name for Mount Cameroon, an active volcano and the highest mountain in West and Central Africa located in southwestern Cameroon.
-
E.
Khondji
Khondji is the surname of Darius Khondji, a renowned cinematographer known for his visually distinctive work on international films.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e25d2593c88190bcdf4a716a94ccb2 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1a0aed374819097d38f51894bee44 |
completed | April 29, 2026, 6:09 a.m. |
Created at: April 17, 2026, 5:32 p.m.