Triple
T3158230
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | I Could Write a Book |
E66040
|
entity |
| Predicate | vocalOrInstrumental |
P25705
|
FINISHED |
| Object | vocal song |
—
|
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: vocal song | Statement: [I Could Write a Book, vocalOrInstrumental, vocal song]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: vocalOrInstrumental Context triple: [I Could Write a Book, vocalOrInstrumental, vocal song]
-
A.
instrumentalIn
Indicates that one entity serves as a crucial means, tool, or contributing factor in bringing about an outcome or enabling another entity’s action or effect.
-
B.
hasVocals
chosen
Indicates that the subject includes or features vocal elements, such as singing or spoken voice, rather than being purely instrumental or non-vocal.
-
C.
hasVocalPerformanceBy
Indicates that a vocal performance in a work or recording is performed by a specified person or group.
-
D.
typeOfInstrument
Indicates the specific kind or category of instrument associated with an entity.
-
E.
vocalArrangement
Indicates the specific way vocal parts or voices are organized, structured, and combined within a musical work or performance.
- 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_69ad85850c1481908a9e9c6242238de2 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada5ec0da88190a83f3448ac76e98e |
completed | March 8, 2026, 4:38 p.m. |
| PD | Predicate disambiguation | batch_69ad9dfbf0348190952a6bca8fc5fed1 |
completed | March 8, 2026, 4:04 p.m. |
Created at: March 8, 2026, 3:05 p.m.