Triple
T15213109
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yle Uutiset |
E363566
|
entity |
| Predicate | partOf |
P40
|
FINISHED |
| Object | Yle |
E365225
|
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: Yle | Statement: [Yle Uutiset, partOf, Yle]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Yle Context triple: [Yle Uutiset, partOf, Yle]
-
A.
Yle
chosen
Yle is Finland’s national public broadcasting company, providing television, radio, and online services in Finnish, Swedish, and other languages.
-
B.
YleX
YleX is a Finnish national radio station aimed primarily at young audiences, focusing on contemporary music, pop culture, and entertainment.
-
C.
Yle Puhe
Yle Puhe is a Finnish Yle radio channel focused on talk programming, including news, current affairs, culture, and in-depth discussions.
-
D.
Yle Radio Suomi
Yle Radio Suomi is Finland’s largest national radio channel, offering news, current affairs, culture, and entertainment programming in Finnish to audiences across the country.
-
E.
Yle Lapset
Yle Lapset is Yleisradio’s dedicated children’s media service, offering age-appropriate TV and digital content for young audiences in Finland.
- 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_69d85a0b78bc8190b6e5ad51a2c4cfc5 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e0076c9e2481909d7a464b2172f4bf |
completed | April 15, 2026, 9:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fed341cfb8819086b386c6cb905eda |
completed | May 9, 2026, 6:25 a.m. |
Created at: April 10, 2026, 3:11 a.m.