Triple
T22873128
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nnedi Okorafor |
E567251
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Okorafor |
—
|
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: Okorafor | Statement: [Nnedi Okorafor, familyName, Okorafor]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Okorafor Context triple: [Nnedi Okorafor, familyName, Okorafor]
-
A.
Okorafor
chosen
Okorafor is the surname of Nnedi Okorafor, a Nigerian-American author renowned for her Africanfuturist and Africanjujuist science fiction and fantasy works.
-
B.
Orjaku
Orjaku is a small village located on the island of Hiiumaa in western Estonia.
-
C.
Dayo Okeniyi
Dayo Okeniyi is a Nigerian-born actor known for roles in films such as "The Hunger Games" and various American television series.
-
D.
Akinwande
Akinwande is the first name of Nigerian playwright, poet, and Nobel laureate Wole Soyinka.
-
E.
Ore Oduba
Ore Oduba is a British television and radio presenter best known for his work on BBC children’s news programme Newsround and for winning Strictly Come Dancing in 2016.
- 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_69e24589d8348190b96422d13a678bc1 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17f55c4b88190adb49871e496ca54 |
completed | April 29, 2026, 3:47 a.m. |
Created at: April 17, 2026, 3:38 p.m.