Triple
T18400763
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Countess Almaviva |
E449985
|
entity |
| Predicate | ensembleNumber |
P111048
|
FINISHED |
| Object | Sull’aria… che soave zeffiretto |
—
|
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: Sull’aria… che soave zeffiretto | Statement: [Countess Almaviva, ensembleNumber, Sull’aria… che soave zeffiretto]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ensembleNumber Context triple: [Countess Almaviva, ensembleNumber, Sull’aria… che soave zeffiretto]
-
A.
ensembleSize
Indicates the number of individual members or participants that make up a given group or ensemble.
-
B.
hasEnsembleNumbers
chosen
Indicates that an entity is associated with one or more ensemble numbers used to identify it within a grouped or collective context.
-
C.
associatedEnsembleOf
Indicates that one entity is linked or connected to a particular ensemble, typically as a member, contributor, or related component of that group.
-
D.
sampleNumber
Indicates that an entity is identified or associated with a specific sample number within a set of samples.
-
E.
typicalEnsembleType
Indicates the usual or characteristic type of ensemble associated with or used to perform a given work, piece, or musical context.
- 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_69d8b9fab8a8819086a9ddc0871715e0 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e5194f2a8c8190afcd7db23e3795fb |
completed | April 19, 2026, 6:05 p.m. |
| PD | Predicate disambiguation | batch_69e44ff1f92c8190afbb8e85d12bf2a9 |
completed | April 19, 2026, 3:45 a.m. |
Created at: April 10, 2026, 10:46 a.m.