Triple
T11679140
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Duke Town |
E277568
|
entity |
| Predicate | foundingEthnicGroup |
P194
|
FINISHED |
| Object | Efik |
E940517
|
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: Efik | Statement: [Duke Town, foundingEthnicGroup, Efik]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Efik Context triple: [Duke Town, foundingEthnicGroup, Efik]
-
A.
Efik
chosen
Efik is a Niger-Congo language spoken primarily by the Efik people in southeastern Nigeria, especially in Cross River State.
-
B.
Nwankwo
Nwankwo is the given name of Nigerian football legend Nwankwo Kanu, a highly decorated forward known for his time at Ajax, Inter Milan, and Arsenal.
-
C.
Dumebi
Dumebi is a popular Afrobeats hit song by Nigerian singer Rema that helped launch him to international prominence.
-
D.
Ahiazu Mbaise
Ahiazu Mbaise is a local government area in southeastern Nigeria known for its predominantly Igbo population and rich cultural traditions.
-
E.
Okpokwu
Okpokwu is a local government area in Benue State, Nigeria, predominantly inhabited by the Idoma people.
- 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_69d6aafd0a448190b44da30af8c6c519 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a461b0908190bef4e1c6777affcf |
completed | April 10, 2026, 7:18 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ef83098e2c819081c22462372f64b4 |
completed | April 27, 2026, 3:38 p.m. |
Created at: April 8, 2026, 9:40 p.m.