PromptEvalLabel
A person's labels on one sampled verdict of a calibration (1.63.0): a verdict per rubric item, keys and values only, never text.
An object with 14 fields.
Fields
| Field | Type | Required | Description |
|---|---|---|---|
arm | PromptEvalArm | yes | |
calibration_id | PromptEvalCalibrationId | yes | |
call_id | CallId | yes | The evaluation Call whose transcript was labelled. |
created_at | Timestamp | yes | |
created_by | ActorRef | yes | |
entry_index | integer | yes | The sample entry it labels. |
id | PromptEvalLabelId | yes | |
items | array of PromptEvalLabelItem | yes | |
object | "prompt_eval_label" | yes | |
repetition | integer | yes | |
run_id | PromptEvalRunId | yes | |
scenario_id | PromptEvalScenarioId | yes | |
scenario_revision | integer | yes | |
suite_id | PromptEvalSuiteId | yes |
Used by
The operations whose parameters, request body or responses name this shape directly.