Triple
T5710719
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | North Korean media |
E125899
|
entity |
| Predicate | foreignMediaAccess |
P6894
|
FINISHED |
| Object | severely restricted |
—
|
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: severely restricted | Statement: [North Korean media, foreignMediaAccess, severely restricted]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: foreignMediaAccess Context triple: [North Korean media, foreignMediaAccess, severely restricted]
-
A.
mediaCovered
Indicates that one entity (such as a media outlet or source) has reported on, featured, or otherwise provided coverage of another entity or event.
-
B.
mediaCoverage
Indicates that one entity reports on, documents, or broadcasts information about another entity through news or media channels.
-
C.
mediaAccess
chosen
Indicates that one entity has the ability, permission, or means to view, use, or interact with a particular media resource.
-
D.
mediaExposure
Indicates the extent to which an entity is subjected to or receives attention from media channels such as television, radio, print, or online platforms.
-
E.
fareMedia
Indicates that a particular type of ticket, pass, or payment instrument is used as the medium for paying a fare.
- 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_69c0082d6fe48190b777fb383769e5c8 |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c029014588819094a2a0f6f9b66bab |
completed | March 22, 2026, 5:38 p.m. |
| PD | Predicate disambiguation | batch_69c021c47f4c81909e6849c3be3e951c |
completed | March 22, 2026, 5:07 p.m. |
Created at: March 22, 2026, 3:46 p.m.