Triple
T14375853
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sky’s triple‑play services |
E356471
|
entity |
| Predicate | televisionServiceType |
P113798
|
FINISHED |
| Object | pay television |
—
|
LITERAL 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: pay television | Statement: [Sky’s triple‑play services, televisionServiceType, pay television]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: televisionServiceType Context triple: [Sky’s triple‑play services, televisionServiceType, pay television]
-
A.
televisionServiceStatus
Indicates the operational or subscription state of a television service for an entity.
-
B.
televisionSystemType
Indicates the type or category of television system associated with an entity (e.g., analog, digital, cable, satellite).
-
C.
televisionPlatform
Indicates that one entity serves as the television platform (e.g., service, system, or distribution channel) through which the other entity’s TV content is delivered or accessed.
-
D.
streamingService
Indicates that one entity provides or delivers media content over the internet to another entity in real time or on demand.
-
E.
televisionNetworkAssociation
Indicates a relationship where an entity is affiliated with, carried by, or part of a particular television network.
- F. None of above. chosen
Provenance (4 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_69d8279163a081908aec45c0e3f1e02f |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de900949fc81909be0da1734c46645 |
completed | April 14, 2026, 7:05 p.m. |
| PD | Predicate disambiguation | batch_69de2a9cb3e081909f6b33fdd939bb9e |
completed | April 14, 2026, 11:53 a.m. |
| PDg | Predicate description generation | batch_69de2e07d1f88190bdcd20967e484718 |
completed | April 14, 2026, 12:07 p.m. |
Created at: April 10, 2026, 1:16 a.m.