Triple
T28379022
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | All Perspectives Ltd |
E718836
|
entity |
| Predicate | ownsMediaBrand |
P59654
|
FINISHED |
| Object | GB News |
—
|
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: GB News | Statement: [All Perspectives Ltd, ownsMediaBrand, GB News]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ownsMediaBrand Context triple: [All Perspectives Ltd, ownsMediaBrand, GB News]
-
A.
mediaOwner
chosen
Indicates that one entity owns, controls, or holds proprietary rights over a media asset or media-related resource associated with another entity.
-
B.
hasMediaCompany
Indicates that one entity owns, controls, or is formally associated with a media company.
-
C.
hasBrandRole
Indicates that an entity holds a specific functional or organizational role in relation to a particular brand.
-
D.
mediaOwnerType
Indicates the type or category of ownership associated with a media asset (e.g., who or what kind of entity owns or controls the media).
-
E.
exportBrand
Indicates a relationship where a brand is sold or distributed outside its home market into foreign or international markets.
- 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_69eff6ee5afc8190bd7375a29f0cc6c6 |
completed | April 27, 2026, 11:53 p.m. |
| NER | Named-entity recognition | batch_69f64cb538448190be1c85c33d6bdd62 |
completed | May 2, 2026, 7:12 p.m. |
| PD | Predicate disambiguation | batch_69f641e2f1708190b45b48d6a43c51d2 |
completed | May 2, 2026, 6:26 p.m. |
Created at: April 28, 2026, 1:05 a.m.