Triple
T23339437
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yesterdays (Art Tatum recording) |
E591694
|
entity |
| Predicate | composerOfOriginalSong |
P140035
|
FINISHED |
| Object | Jerome Kern |
—
|
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: Jerome Kern | Statement: [Yesterdays (Art Tatum recording), composerOfOriginalSong, Jerome Kern]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: composerOfOriginalSong Context triple: [Yesterdays (Art Tatum recording), composerOfOriginalSong, Jerome Kern]
-
A.
composerOfOriginalSongs
chosen
Indicates that one entity is the composer who created the original songs associated with another entity.
-
B.
songWrittenBy
Indicates that a particular song was created or composed by a specific person or group.
-
C.
originalArtistOfSong
Indicates that one entity is the artist who first created or performed the specified song.
-
D.
composerOfSongsInWork
Indicates that one entity is the composer of the songs contained within a particular work (such as a film, play, or album).
-
E.
originalLyricistOfCoveredSong
Indicates that one entity is the original lyricist who wrote the lyrics for a song that is being covered by another performer or recording.
- 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_69e25d20156c81908c5c53195bd9c738 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f198317f4c8190a557cacb86568d6c |
completed | April 29, 2026, 5:33 a.m. |
| PD | Predicate disambiguation | batch_69effcfd8d288190937a887fe6023c11 |
completed | April 28, 2026, 12:19 a.m. |
Created at: April 17, 2026, 5:17 p.m.