Triple
T1142221
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NBC Blue Network |
E23477
|
entity |
| Predicate | programDistribution |
P10379
|
FINISHED |
| Object | affiliate stations |
—
|
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: affiliate stations | Statement: [NBC Blue Network, programDistribution, affiliate stations]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: programDistribution Context triple: [NBC Blue Network, programDistribution, affiliate stations]
-
A.
distributesIn
Indicates that one entity allocates or hands out something (e.g., items, resources, information) within or across a specified area, group, or context.
-
B.
programType
Indicates the category or kind of program to which an entity belongs or with which it is associated.
-
C.
hasDistributions
chosen
Indicates that an entity is associated with one or more distributions through which it is delivered, provided, or made available.
-
D.
distributionMethod
Indicates the means or channel through which something (such as a product, resource, or information) is delivered or made available to recipients.
-
E.
distributedAs
Indicates that something is allocated, delivered, or spread out according to a particular pattern, rule, or distribution scheme.
- 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_69a493ef399c8190b04b9146d2314f59 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4bc4d414881908fc636e8ccbc4c34 |
completed | March 1, 2026, 10:23 p.m. |
| PD | Predicate disambiguation | batch_69a4bb4d4104819084027a043c6118cb |
completed | March 1, 2026, 10:18 p.m. |
Created at: March 1, 2026, 7:44 p.m.