Triple
T16612947
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | XERB radio broadcasts |
E403621
|
entity |
| Predicate | advertisingType |
P33256
|
FINISHED |
| Object | mail-order products |
—
|
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: mail-order products | Statement: [XERB radio broadcasts, advertisingType, mail-order products]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: advertisingType Context triple: [XERB radio broadcasts, advertisingType, mail-order products]
-
A.
hasAdvertisingVisual
Indicates that an entity includes, is associated with, or uses a specific visual element or asset for advertising purposes.
-
B.
usesAdvertisingModel
Indicates that one entity employs or relies on another entity’s advertising-based business or revenue model.
-
C.
advertisedUsing
chosen
Indicates that something is promoted or made known through a particular medium, method, or channel of advertising.
-
D.
campaignType
Indicates the specific category or kind of campaign an entity is associated with or participates in.
-
E.
advertisingLocation
Indicates the place or medium where an advertisement is displayed or presented.
- 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_69d883880d0c81908b5fcd454e767b60 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e3609776d48190b6b8c7826ac575c4 |
completed | April 18, 2026, 10:44 a.m. |
| PD | Predicate disambiguation | batch_69e296aabc508190b3836a91b49113ad |
completed | April 17, 2026, 8:23 p.m. |
Created at: April 10, 2026, 5:17 a.m.