Triple
T24029109
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2018 Indian Premier League |
E595044
|
entity |
| Predicate | broadcastPartnerIndia |
P140497
|
FINISHED |
| Object | Star Sports |
—
|
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: Star Sports | Statement: [2018 Indian Premier League, broadcastPartnerIndia, Star Sports]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: broadcastPartnerIndia Context triple: [2018 Indian Premier League, broadcastPartnerIndia, Star Sports]
-
A.
notableBroadcastPartners
chosen
Indicates that an entity has significant or prominent broadcast partners with which it has had important media or transmission relationships.
-
B.
broadcastNetwork
Indicates that one entity serves as the television or radio network that broadcasts the programming or content of another entity.
-
C.
broadcasterCountry
Indicates the country from which a broadcaster operates or holds its primary broadcasting license.
-
D.
tvPartner
Indicates that two entities are partners or collaborators in the context of television, such as co-producing, co-presenting, or jointly participating in TV-related activities.
-
E.
broadcasterAbbreviation
Indicates that an entity is identified by a specific abbreviated name used by a broadcaster.
- F. None of above.
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_69e288bf45f08190a1b6ed8cd0b9e86b |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1d76e10fc8190afa60c618a4398ee |
completed | April 29, 2026, 10:03 a.m. |
| PD | Predicate disambiguation | batch_69f1764345388190a3102b62ddb729b4 |
completed | April 29, 2026, 3:08 a.m. |
Created at: April 17, 2026, 9:54 p.m.