Triple
T20843114
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Peter Akinola |
E513150
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Peter Jasper Akinola |
—
|
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: Peter Jasper Akinola | Statement: [Peter Akinola, name, Peter Jasper Akinola]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Peter Jasper Akinola Context triple: [Peter Akinola, name, Peter Jasper Akinola]
-
A.
Peter Akinola
chosen
Peter Akinola is a Nigerian Anglican archbishop known for his conservative theological stance and influential leadership within the global Anglican Communion.
-
B.
Kevin Olusola
Kevin Olusola is an American musician best known as the beatboxer and cellist of the a cappella group Pentatonix.
-
C.
Michael Ajao
Michael Ajao is a British actor known for his role in the psychological horror film "Last Night in Soho."
-
D.
Rilwan Akiolu
Rilwan Akiolu is a Nigerian traditional ruler and former police officer who serves as the Oba (king) of Lagos, one of the most influential monarchs in southwestern Nigeria.
-
E.
Rafael Akinyemi
Rafael Akinyemi is a songwriter known for his association with the musical project Womanizer.
- 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_69e0b4f4898081908209e58edb8f9c45 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c34cdf9881909f3340874bbee5bc |
completed | April 21, 2026, 12:22 a.m. |
Created at: April 16, 2026, 12:43 p.m.