Triple
T14283424
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Channel Four Wales |
E354106
|
entity |
| Predicate | primaryContentFocus |
P4446
|
FINISHED |
| Object | Welsh-language content |
—
|
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: Welsh-language content | Statement: [Channel Four Wales, primaryContentFocus, Welsh-language content]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryContentFocus Context triple: [Channel Four Wales, primaryContentFocus, Welsh-language content]
-
A.
primaryContent
chosen
Indicates that one entity serves as the main or most important content associated with another entity.
-
B.
primaryTopicOf
Indicates that a given subject is the main or central topic described by another resource (such as a document, page, or record).
-
C.
primaryContentRegion
Indicates the main area or section where the most important or central content is located or presented.
-
D.
primaryTrainingFocus
Indicates the main area or aspect that training is chiefly directed toward or concentrated on.
-
E.
primaryTextualFocus
Indicates that one entity is the main subject or central topic emphasized within the text of another entity.
- 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_69d8278d25148190abf1a8c8f5f533ad |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de697d9fd08190b0cd7a6a6737ba03 |
completed | April 14, 2026, 4:21 p.m. |
| PD | Predicate disambiguation | batch_69de2a88446481909cd526da97a3b70f |
completed | April 14, 2026, 11:52 a.m. |
Created at: April 10, 2026, 1:10 a.m.