Triple
T22369478
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nnamdi Azikiwe |
E553000
|
entity |
| Predicate | isKnownAs |
P39
|
FINISHED |
| Object | “Zik of Africa” |
—
|
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: “Zik of Africa” | Statement: [Nnamdi Azikiwe, isKnownAs, “Zik of Africa”]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: “Zik of Africa” Context triple: [Nnamdi Azikiwe, isKnownAs, “Zik of Africa”]
-
A.
Zik
chosen
Zik is the popular nickname of Nnamdi Azikiwe, a leading Nigerian nationalist and the first President of Nigeria.
-
B.
Jive Afrika
Jive Afrika is a music label under the Zomba Group of Companies, known for producing and promoting African artists and recordings.
-
C.
Zikz
Zikz is the in-game name of Tony "Zikz" Gray, a professional esports coach best known for his work in competitive League of Legends.
-
D.
Afrikan Boy
Afrikan Boy is a British-Nigerian grime and hip-hop artist known for blending Afrobeat influences with UK urban sounds and humorous, socially aware lyrics.
-
E.
Zulu Screams
"Zulu Screams" is a 2019 Afrobeat-influenced hip-hop single by American rapper GoldLink featuring Maleek Berry and Bibi Bourelly.
- 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_69e11e4affcc8190ba7c27d29062558d |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f158032b748190ad36c7e3809304e9 |
completed | April 29, 2026, 12:59 a.m. |
Created at: April 16, 2026, 8:44 p.m.