Triple
T10777777
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Akinwumi Adesina |
E254240
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object |
Adesina
Adesina is a Yoruba surname notably borne by Akinwumi Adesina, the Nigerian economist and President of the African Development Bank.
|
E886263
|
NE FINISHED |
How this triple was built (4 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: Adesina | Statement: [Akinwumi Adesina, familyName, Adesina]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Adesina Context triple: [Akinwumi Adesina, familyName, Adesina]
-
A.
Bisi Akande
Bisi Akande is a Nigerian politician and statesman, best known as a former governor of Osun State and a key founding leader of major progressive political parties in Nigeria.
-
B.
Funmi Adeola
Funmi Adeola is a character in the Doctor Who universe, known as the sister of Tanya Adeola in the spin-off series "Class."
-
C.
Theodosia Okoh
Theodosia Okoh was a Ghanaian artist and teacher best known for creating Ghana’s national flag.
-
D.
Adeola
Adeola is a Yoruba-origin surname and given name commonly used in Nigeria and among the Yoruba diaspora.
-
E.
Adenike Balogun
Adenike Balogun is a fictional character portrayed as the mother of George, serving as a central figure in his story.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Adesina Triple: [Akinwumi Adesina, familyName, Adesina]
Generated description
Adesina is a Yoruba surname notably borne by Akinwumi Adesina, the Nigerian economist and President of the African Development Bank.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Adesina Target entity description: Adesina is a Yoruba surname notably borne by Akinwumi Adesina, the Nigerian economist and President of the African Development Bank.
-
A.
Bisi Akande
Bisi Akande is a Nigerian politician and statesman, best known as a former governor of Osun State and a key founding leader of major progressive political parties in Nigeria.
-
B.
Funmi Adeola
Funmi Adeola is a character in the Doctor Who universe, known as the sister of Tanya Adeola in the spin-off series "Class."
-
C.
Theodosia Okoh
Theodosia Okoh was a Ghanaian artist and teacher best known for creating Ghana’s national flag.
-
D.
Adeola
Adeola is a Yoruba-origin surname and given name commonly used in Nigeria and among the Yoruba diaspora.
-
E.
Adenike Balogun
Adenike Balogun is a fictional character portrayed as the mother of George, serving as a central figure in his story.
- F. None of above. chosen
Provenance (5 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_69d6aa609f008190a294200aefcb7bd5 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d732c18c3c819089d49e3e4585049e |
completed | April 9, 2026, 5:01 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69de55daf52c8190aee3bca39cdc5d55 |
completed | April 14, 2026, 2:57 p.m. |
| NEDg | Description generation | batch_69de5eacae148190b7ca2da87427572e |
completed | April 14, 2026, 3:35 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69de6397ff688190b6788489895a5360 |
completed | April 14, 2026, 3:56 p.m. |
Created at: April 8, 2026, 9:16 p.m.