Triple
T31314777
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | You’re Not Sorry (Taylor’s Version) |
E798561
|
entity |
| Predicate | hasOriginalReleaseYearOfSourceSong |
P114546
|
FINISHED |
| Object | 2008 |
—
|
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: 2008 | Statement: [You’re Not Sorry (Taylor’s Version), hasOriginalReleaseYearOfSourceSong, 2008]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasOriginalReleaseYearOfSourceSong Context triple: [You’re Not Sorry (Taylor’s Version), hasOriginalReleaseYearOfSourceSong, 2008]
-
A.
originalReleaseYearOfSourceSong
chosen
Indicates the calendar year in which the source song was first officially released.
-
B.
hasOriginalSongReleaseDecade
Indicates the decade during which the original version of a song was first released.
-
C.
hasOriginalAlbumRelease
Indicates that an album or musical work is associated with its first official release instance or edition.
-
D.
hasOriginalReleaseArtist
Indicates that an entity (such as a work or recording) is associated with the artist who first released it.
-
E.
hasOriginalMusicBy
Indicates that the original musical score or soundtrack for a work was created or composed by a specified 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_69fd592e48cc81909d754cc6c4bd99ae |
completed | May 8, 2026, 3:31 a.m. |
| PD | Predicate disambiguation | batch_69fd58b7f9b881909dc099b28d567784 |
completed | May 8, 2026, 3:30 a.m. |
Created at: April 29, 2026, 9:15 p.m.