Triple
T12225896
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ekpeye |
E291350
|
entity |
| Predicate | neighboringEthnicGroup |
P11274
|
FINISHED |
| Object | Ikwere |
E376326
|
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: Ikwere | Statement: [Ekpeye, neighboringEthnicGroup, Ikwere]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ikwere Context triple: [Ekpeye, neighboringEthnicGroup, Ikwere]
-
A.
Ikwere
chosen
Ikwere is an ethnic group and language community primarily located in Rivers State in the Niger Delta region of Nigeria.
-
B.
Osogbo
Osogbo is a major city in southwestern Nigeria known for its rich Yoruba cultural heritage and the UNESCO-listed Osun-Osogbo Sacred Grove.
-
C.
Ogboru
Ogboru is a traditional deity revered by the Urhobo people of Nigeria, associated with their indigenous religious beliefs and cultural practices.
-
D.
Ejisu
Ejisu is a prominent town and municipal capital in Ghana’s Ashanti Region, known for its historical significance within the Ashanti Kingdom and its role as a commercial and administrative center.
-
E.
Ifewara
Ifewara is a notable town in southwestern Nigeria associated with the Ijesha people and culture.
- 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_69d6ab668acc8190963ba424049d6aee |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d91ca2101c8190955c36704935036a |
completed | April 10, 2026, 3:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f62a8e6ba081908428ce11196815cc |
completed | May 2, 2026, 4:47 p.m. |
Created at: April 8, 2026, 9:51 p.m.