Triple
T12888303
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Onikan |
E308289
|
entity |
| Predicate | hasLandmark |
P105
|
FINISHED |
| Object | Onikan Stadium |
E274576
|
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: Onikan Stadium | Statement: [Onikan, hasLandmark, Onikan Stadium]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Onikan Stadium Context triple: [Onikan, hasLandmark, Onikan Stadium]
-
A.
Onikan Stadium
chosen
Onikan Stadium is a historic multi-purpose sports arena located on Lagos Island in Lagos, Nigeria.
-
B.
Setsoto Stadium
Setsoto Stadium is a multi-purpose national sports venue in Maseru, Lesotho, primarily used for football matches and major public events.
-
C.
Japoma Stadium
Japoma Stadium is a major multi-purpose sports venue in Douala, Cameroon, best known for hosting top-level football matches including those of the Cameroon national team and international tournaments.
-
D.
Ajinomoto Stadium
Ajinomoto Stadium is a large multi-purpose sports venue in Tokyo, Japan, best known for hosting professional football matches and major sporting events.
-
E.
Edogawa Stadium
Edogawa Stadium is a multi-purpose sports venue in Tokyo, Japan, primarily used for athletics and football matches.
- 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_69d7bdf7c1f0819098102569a8d8cbf5 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d9714581988190afc720ffd7797860 |
completed | April 10, 2026, 9:53 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6a5576ae4819084914697b2e86d9f |
completed | May 3, 2026, 1:31 a.m. |
Created at: April 9, 2026, 5:39 p.m.