Triple
T22854088
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ake Palace |
E566431
|
entity |
| Predicate | traditionalSeatOf |
P16984
|
FINISHED |
| Object | Alake of Egbaland |
—
|
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: Alake of Egbaland | Statement: [Ake Palace, traditionalSeatOf, Alake of Egbaland]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Alake of Egbaland Context triple: [Ake Palace, traditionalSeatOf, Alake of Egbaland]
-
A.
Alake of Egbaland
chosen
The Alake of Egbaland is the traditional paramount ruler of the Egba people in Abeokuta, Ogun State, Nigeria.
-
B.
Egba territory
Egba territory was a historical Yoruba region in what is now southwestern Nigeria, centered around Abeokuta and inhabited predominantly by the Egba people.
-
C.
Akoko region
The Akoko region is an area in southwestern Nigeria known for its cluster of closely related Akoko communities and their distinct languages and cultural traditions.
-
D.
Akoko South
Akoko South is a local government area in Ondo State, southwestern Nigeria, forming part of the larger Akoko region.
-
E.
Egbeda
Egbeda is a densely populated residential and commercial neighborhood in Lagos, Nigeria, known for its busy markets, nightlife, and proximity to major transport routes.
- 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_69e2458750b481908a8e4cf4609cc6cf |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17ebb4ea48190b4b865e316f6a75f |
completed | April 29, 2026, 3:44 a.m. |
Created at: April 17, 2026, 3:37 p.m.