Triple
T36327509
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ain't No Song |
E894524
|
entity |
| Predicate | lyricsCreator |
P171650
|
FINISHED |
| Object | James Taylor |
—
|
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: James Taylor | Statement: [Ain't No Song, lyricsCreator, James Taylor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lyricsCreator Context triple: [Ain't No Song, lyricsCreator, James Taylor]
-
A.
writesLyrics
chosen
Indicates that one entity creates or composes song lyrics for another entity (such as a song, musical work, or artist).
-
B.
lyricImagery
Indicates that one entity uses vivid, descriptive language to create sensory or imaginative images in the lyrics of another entity.
-
C.
lyricFunction
Indicates the role or purpose that a set of lyrics serves within a musical work or performance.
-
D.
lyricText
Indicates that one entity is the lyrical content or words of a song or musical piece associated with another entity.
-
E.
hasLyricalWritingFor
Indicates that one entity provides or is characterized by lyrical or poetic writing created for 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_69f76e4dcf088190a6c3216c209cab52 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7ba6d06f48190a71b5a2f19e2232f |
completed | May 3, 2026, 9:13 p.m. |
| PD | Predicate disambiguation | batch_69f7b9a4aad48190a62e41c5e39339d9 |
completed | May 3, 2026, 9:09 p.m. |
Created at: May 3, 2026, 4:09 p.m.