Triple
T18098157
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | "Mustang Sally" (Wilson Pickett song) |
E433141
|
entity |
| Predicate | lyricalCatchphrase |
P32220
|
FINISHED |
| Object | "ride, Sally, ride" |
—
|
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: "ride, Sally, ride" | Statement: ["Mustang Sally" (Wilson Pickett song), lyricalCatchphrase, "ride, Sally, ride"]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lyricalCatchphrase Context triple: ["Mustang Sally" (Wilson Pickett song), lyricalCatchphrase, "ride, Sally, ride"]
-
A.
lyricalPhrase
Indicates that one entity is a lyrical phrase or line that is part of, derived from, or associated with another entity such as a song, poem, or musical work.
-
B.
featuresCatchphrase
Indicates that an entity prominently includes or is associated with a particular catchphrase.
-
C.
lyricFunction
Indicates the role or purpose that a set of lyrics serves within a musical work or performance.
-
D.
refrainText
chosen
Indicates that a piece of text functions as the recurring refrain or repeated line within a larger work, such as a song or poem.
-
E.
lyricalMotive
Indicates a recurring musical or textual idea that serves as a unifying expressive element within a lyrical or vocal work.
- 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_69d8b90916008190a1f110bd7ced5473 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4ddb3ef548190a322f98917b54a59 |
completed | April 19, 2026, 1:50 p.m. |
| PD | Predicate disambiguation | batch_69e4330e1f2881908b2506d47c48736b |
completed | April 19, 2026, 1:42 a.m. |
Created at: April 10, 2026, 10:27 a.m.