Triple
T32854473
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Streams |
E840338
|
entity |
| Predicate | featuresImprovisationStyle |
P85584
|
FINISHED |
| Object | avant-garde improvisation |
—
|
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: avant-garde improvisation | Statement: [Streams, featuresImprovisationStyle, avant-garde improvisation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuresImprovisationStyle Context triple: [Streams, featuresImprovisationStyle, avant-garde improvisation]
-
A.
hasImprovisationStyle
chosen
Indicates that an entity exhibits or is associated with a particular style or manner of improvisation.
-
B.
hasImprovisation
Indicates that an entity includes, involves, or is characterized by improvisational elements or unscripted creative actions in relation to another entity or context.
-
C.
hasImprovisationFrom
Indicates that something includes or is derived from an improvisational performance or source.
-
D.
featuresRichHarmonies
Indicates that the subject contains or employs complex, layered, and sonically dense harmonic structures.
-
E.
featuresVocalImprovisation
Indicates that the action or event includes or showcases spontaneous, unscripted vocal performance or embellishment.
- 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_69f349412c78819084459850e11d29f7 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_6a0141fceb908190863778741bd4487d |
completed | May 11, 2026, 2:42 a.m. |
| PD | Predicate disambiguation | batch_6a0141a9628c819090c0b24ce052a2fb |
completed | May 11, 2026, 2:40 a.m. |
Created at: May 1, 2026, 1:17 a.m.