Triple
T13781925
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Matchroom Sport |
E331150
|
entity |
| Predicate | hasMediaPartner |
P8946
|
FINISHED |
| Object | DAZN |
E122126
|
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: DAZN | Statement: [Matchroom Sport, hasMediaPartner, DAZN]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: DAZN Context triple: [Matchroom Sport, hasMediaPartner, DAZN]
-
A.
DAZN
chosen
DAZN is a global sports streaming service that broadcasts live and on-demand sporting events over the internet.
-
B.
Fubo
Fubo is a live TV streaming service best known for its extensive sports-focused channel lineup and cord-cutting alternative to traditional cable.
-
C.
Fox Sports Go
Fox Sports Go was a streaming service and app from Fox Sports that allowed viewers to watch live and on-demand sports content from Fox’s TV networks.
-
D.
ESPN+ (streaming service)
ESPN+ is a subscription-based sports streaming service offering live events, original programming, and on-demand content primarily focused on U.S. and international sports.
-
E.
5 Live Sport
5 Live Sport is a flagship BBC Radio 5 Live programme providing live commentary, analysis, and coverage of major sporting events in the UK and worldwide.
- 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_69d81c583b0081909e408a17db517a21 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de0247ccc881908dad7b547221f15d |
completed | April 14, 2026, 9 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7b079013881908e9f5412e5dfb0b2 |
completed | May 3, 2026, 8:30 p.m. |
Created at: April 9, 2026, 10:11 p.m.