Triple
T31315899
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mine (Taylor’s Version) |
E798594
|
entity |
| Predicate | hasOriginalSongArtist |
P146258
|
FINISHED |
| Object | Taylor Swift |
—
|
NE NERFINISHED |
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: Taylor Swift | Statement: [Mine (Taylor’s Version), hasOriginalSongArtist, Taylor Swift]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasOriginalSongArtist Context triple: [Mine (Taylor’s Version), hasOriginalSongArtist, Taylor Swift]
-
A.
hasOriginalReleaseArtist
Indicates that an entity (such as a work or recording) is associated with the artist who first released it.
-
B.
hasOriginalAlbumArtist
Indicates that an album is associated with the artist who is credited as its original primary creator or performer.
-
C.
hasOriginalLyricist
Indicates that an entity (such as a musical or song) is associated with the person who first wrote its lyrics.
-
D.
originalArtistOfSong
chosen
Indicates that one entity is the artist who first created or performed the specified song.
-
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_69fd67191cf88190b53ecbf5be3564e9 |
completed | May 8, 2026, 4:31 a.m. |
| PD | Predicate disambiguation | batch_69fd654fdaac81908e67e75194710f06 |
completed | May 8, 2026, 4:23 a.m. |
Created at: April 29, 2026, 9:15 p.m.