Triple
T12350440
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aisha Buhari |
E294469
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Buhari |
E61201
|
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: Buhari | Statement: [Aisha Buhari, familyName, Buhari]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Buhari Context triple: [Aisha Buhari, familyName, Buhari]
-
A.
Muhammadu Buhari
chosen
Muhammadu Buhari is a Nigerian politician and retired major general who served as the President of Nigeria from 2015 to 2023.
-
B.
Bola Tinubu
Bola Tinubu is a Nigerian politician and former governor of Lagos State who became president of Nigeria in 2023.
-
C.
Oluremi Tinubu
Oluremi Tinubu is a Nigerian politician and former First Lady of Lagos State who serves as the First Lady of Nigeria and has been a prominent senator and advocate for social and women’s issues.
-
D.
Goodluck Jonathan
Goodluck Jonathan is a Nigerian politician who served as President of Nigeria from 2010 to 2015, a period marked by significant security challenges and political reforms.
-
E.
Yemi Osinbajo
Yemi Osinbajo is a Nigerian lawyer, professor of law, and politician who served as the Vice President of Nigeria from 2015 to 2023.
- 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_69d6ab6ccbec8190b09e2d357aa80064 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d93f7cbff08190849cd2aec4ce3243 |
completed | April 10, 2026, 6:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f69b7e7454819099d89db93d0fc1ea |
completed | May 3, 2026, 12:49 a.m. |
Created at: April 8, 2026, 9:53 p.m.