Triple
T3360685
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dancing on the Ceiling |
E70712
|
entity |
| Predicate | backingVocals |
P28444
|
FINISHED |
| Object | layered harmonies |
—
|
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: layered harmonies | Statement: [Dancing on the Ceiling, backingVocals, layered harmonies]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: backingVocals Context triple: [Dancing on the Ceiling, backingVocals, layered harmonies]
-
A.
hasBackingVocals
chosen
Indicates that one musical performance, track, or part includes supporting vocal contributions accompanying a primary vocal line.
-
B.
secondaryVocalist
Indicates that an entity performs as a supporting or backup singer in a vocal performance, rather than as the primary lead vocalist.
-
C.
hasVocals
Indicates that the subject includes or features vocal elements, such as singing or spoken voice, rather than being purely instrumental or non-vocal.
-
D.
hasVocalPerformanceBy
Indicates that a vocal performance in a work or recording is performed by a specified person or group.
-
E.
includesScratchVocalsFrom
Indicates that one audio recording or track contains scratch (temporary or demo) vocal parts taken from another recording or session.
- 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_69ad85a660c48190998489309a3b4869 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb267ec1081909a4e3e227d5bad01 |
completed | March 8, 2026, 5:31 p.m. |
| PD | Predicate disambiguation | batch_69ada4317e288190ab7d0f66e9dba65f |
completed | March 8, 2026, 4:30 p.m. |
Created at: March 8, 2026, 3:13 p.m.