Triple
T16582112
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Niger River Bridge |
E402859
|
entity |
| Predicate | connects |
P390
|
FINISHED |
| Object | Asaba |
E254229
|
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: Asaba | Statement: [Niger River Bridge, connects, Asaba]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Asaba Context triple: [Niger River Bridge, connects, Asaba]
-
A.
Asaba
chosen
Asaba is the capital city of Delta State in southern Nigeria, situated on the western bank of the River Niger and serving as an important administrative and commercial center.
-
B.
Arugba
Arugba is the virgin priestess who carries sacrificial offerings to the Osun River during the annual Osun-Osogbo Festival in Nigeria.
-
C.
Udichi
Udichi is a section or unit within the Uttarayan Complex, likely serving as one of its residential or functional blocks.
-
D.
Azumah
Azumah is a Ghanaian given name most famously borne by legendary world champion boxer Azumah Nelson.
-
E.
Iju-Ota
Iju-Ota is a prominent urban and industrial town in Ogun State, southwestern Nigeria, known for its role in regional commerce and manufacturing.
- 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_69d88387363c8190a97a0c942130de97 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e35998371c8190936dcdaab5ca7e21 |
completed | April 18, 2026, 10:14 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a006ef0bc4c8190b06b03c06d344abf |
completed | May 10, 2026, 11:41 a.m. |
Created at: April 10, 2026, 5:16 a.m.