Triple
T13970739
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NBC News Today |
E336054
|
entity |
| Predicate | hasContentMix |
P105862
|
FINISHED |
| Object | hard news and soft news |
—
|
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: hard news and soft news | Statement: [NBC News Today, hasContentMix, hard news and soft news]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasContentMix Context triple: [NBC News Today, hasContentMix, hard news and soft news]
-
A.
hasContentFrom
Indicates that one entity’s content is derived from, includes, or is based on another entity.
-
B.
hasInteriorContentType
chosen
Indicates that something contains internal material or content of a specified type.
-
C.
hasBroadcastContent
Indicates that one entity (typically a broadcast or channel) carries, includes, or transmits the specified content.
-
D.
mixesWith
Indicates that one entity is combined or blended together with another entity to form a mixture.
-
E.
mixedAt
Indicates that one entity has been combined or blended together with another entity (or entities), typically to form a mixture at a specific time or place.
- 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_69d81c61f3508190aaf2ca0dc0002c59 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de2e8eae40819080dd4bd25c73b6d6 |
completed | April 14, 2026, 12:09 p.m. |
| PD | Predicate disambiguation | batch_69dd465a21408190b912a42c50ffa0d9 |
completed | April 13, 2026, 7:39 p.m. |
Created at: April 9, 2026, 10:18 p.m.