Triple
T26341728
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sirius XM Holdings Inc. |
E662663
|
entity |
| Predicate | hasPrimaryRevenueModel |
P94216
|
FINISHED |
| Object | subscription fees |
—
|
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: subscription fees | Statement: [Sirius XM Holdings Inc., hasPrimaryRevenueModel, subscription fees]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPrimaryRevenueModel Context triple: [Sirius XM Holdings Inc., hasPrimaryRevenueModel, subscription fees]
-
A.
hasSecondaryRevenueModel
Indicates that an entity has an additional, non-primary way of generating revenue beyond its main business model.
-
B.
hasBroadcastRevenueModel
Indicates that one entity uses or is associated with a particular revenue model based on broadcasting activities.
-
C.
hadPrimaryBusinessModel
Indicates that an entity’s main or central way of generating revenue or creating economic value was based on a specified business model.
-
D.
usesRevenueModel
chosen
Indicates that one entity applies or operates according to a particular revenue model to generate income.
-
E.
hasRevenueUnit
Indicates that an entity’s revenue is measured, reported, or associated in terms of a specified unit (e.g., currency or measurement unit).
- 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_69ee81304194819092e20e0fae3aee07 |
completed | April 26, 2026, 9:18 p.m. |
| NER | Named-entity recognition | batch_69fcab6e888881908ca9e18660928a40 |
completed | May 7, 2026, 3:10 p.m. |
| PD | Predicate disambiguation | batch_69fc4562a5b88190bad48f083a6dcdfa |
completed | May 7, 2026, 7:55 a.m. |
Created at: April 26, 2026, 10:39 p.m.