Triple
T31314778
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | You’re Not Sorry (Taylor’s Version) |
E798561
|
entity |
| Predicate | hasReRecordingContext |
P114547
|
FINISHED |
| Object | artist reclaiming master rights |
—
|
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: artist reclaiming master rights | Statement: [You’re Not Sorry (Taylor’s Version), hasReRecordingContext, artist reclaiming master rights]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasReRecordingContext Context triple: [You’re Not Sorry (Taylor’s Version), hasReRecordingContext, artist reclaiming master rights]
-
A.
hasReRecordingPurpose
chosen
Indicates that an entity is associated with a specific purpose or intent for which a recording is being re-recorded.
-
B.
hasRe-recording
Indicates that one recording is a new or updated version made again from the same original material or performance.
-
C.
isReRecording
Indicates that an existing recording is being recorded again, typically to replace, update, or improve the original version.
-
D.
hasRecordingWith
Indicates that one entity is associated with or includes a particular recording as part of its content or representation.
-
E.
hasReRecordingCredit
Indicates that an entity is credited for re-recording existing audio or musical material associated with another entity.
- 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_69f224e1932c81908fef14f7b03a10b7 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_6a0136e4af808190b529d324bbf0c5d9 |
completed | May 11, 2026, 1:54 a.m. |
| PD | Predicate disambiguation | batch_6a01369141c4819091cb8064913a44ca |
completed | May 11, 2026, 1:53 a.m. |
Created at: April 29, 2026, 9:15 p.m.