Triple
T16529835
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Coventrians |
E401533
|
entity |
| Predicate | hasNotableCityFeature |
P1495
|
FINISHED |
| Object | Ricoh Arena |
E793112
|
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: Ricoh Arena | Statement: [Coventrians, hasNotableCityFeature, Ricoh Arena]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ricoh Arena Context triple: [Coventrians, hasNotableCityFeature, Ricoh Arena]
-
A.
Ricoh Arena
chosen
Ricoh Arena is a multi-purpose sports and entertainment stadium complex in Coventry, England, best known for hosting football matches and major events.
-
B.
TUI Arena
TUI Arena is a large multi-purpose indoor arena in Hanover, Germany, best known for hosting major ice hockey games, concerts, and other large-scale events.
-
C.
Accor Arena
Accor Arena is a major multi-purpose indoor venue in Paris, France, known for hosting large-scale sports events, concerts, and entertainment shows.
-
D.
Steel Arena
Steel Arena is a major indoor ice hockey and multi-purpose sports and entertainment venue located in Košice, Slovakia.
-
E.
Barclaycard Arena
Barclaycard Arena is a major multi-purpose indoor arena in Hamburg, Germany, hosting ice hockey games, concerts, and other large-scale events.
- 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_69d883838abc8190bc79cb2d41733ce2 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e32ed625208190a68b879266b05b3f |
completed | April 18, 2026, 7:12 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00608efd0c81908e64419bd74eb285 |
completed | May 10, 2026, 10:40 a.m. |
Created at: April 10, 2026, 5:14 a.m.