Triple
T21598243
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sazka Arena |
E532958
|
entity |
| Predicate | owner |
P347
|
FINISHED |
| Object | Bestsport |
—
|
NE NERFINISHED |
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: Bestsport | Statement: [Sazka Arena, owner, Bestsport]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bestsport Context triple: [Sazka Arena, owner, Bestsport]
-
A.
Bestsport
chosen
Bestsport is a Czech sports and entertainment management company known for operating major venues and events, including Prague’s O2 Arena.
-
B.
WinSport
WinSport is a Canadian non-profit organization that owns and operates Olympic legacy sports facilities in Calgary, promoting winter sport development and high-performance training.
-
C.
Kayo Sports
Kayo Sports is an Australian sports streaming service offering live and on-demand coverage of local and international sporting events.
-
D.
Decathlon
Decathlon is a classic multi-sport track and field video game designed by David Crane, known for challenging players to compete across ten Olympic-style events.
-
E.
Casa Sports
Casa Sports is a prominent professional football club from Senegal that competes in the country’s top-tier league and is known for its strong regional support and competitive performances.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c46364608190a337dc8720dc2a35 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69eefae2fc908190b989f39e8cefffb2 |
completed | April 27, 2026, 5:57 a.m. |
Created at: April 16, 2026, 6:32 p.m.