Triple
T32081562
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Magnatune |
E819310
|
entity |
| Predicate | revenueSharingModel |
P164478
|
FINISHED |
| Object | 50-50 revenue split with artists |
—
|
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: 50-50 revenue split with artists | Statement: [Magnatune, revenueSharingModel, 50-50 revenue split with artists]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: revenueSharingModel Context triple: [Magnatune, revenueSharingModel, 50-50 revenue split with artists]
-
A.
requiresRevenueSharingWith
Indicates that one party must share a portion of its revenue with another party as a condition of their relationship or agreement.
-
B.
usesRevenueModel
Indicates that one entity applies or operates according to a particular revenue model to generate income.
-
C.
profitShareFraction
Indicates the proportion of total profit that is allocated or distributed to a particular party.
-
D.
revenueDivision
chosen
Indicates how total revenue is allocated or split among different parties or components.
-
E.
dataSharingModel
Indicates a relationship where one entity defines or uses a structured approach or framework for how data is shared between parties.
- 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_69f348ff8ef88190931c08ba530a36bc |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6b580c3e481909f45d1716cde89ad |
completed | May 3, 2026, 2:40 a.m. |
| PD | Predicate disambiguation | batch_69f6b3a7bdb481908d16a32f49e38c2c |
completed | May 3, 2026, 2:32 a.m. |
Created at: May 1, 2026, 12:24 a.m.