surface↓classification↓timeframe
Classificationdimension · returns varchar

TIMEFRAME

Extract timeframe dimension via zero-shot NLI

Per-row classifier — stable across GROUP BY.

classificationnlispecialist-zoodate

Arguments

nametypedescription
textVARCHAR—
granularityVARCHAR—

About

Timeframe extractor — identifies when events in the text occurred or will occur. The `granularity` argument picks which time axis to bucket on: time_of_day, season, weather, or duration. Backend: specialist zoo zero-shot NLI via /classify_batch. Each granularity has its own fixed label set and hypothesis template. Granularity options: - time_of_day: Morning / Afternoon / Evening / Night / Late night / Dawn / Dusk - season: Spring / Summer / Fall / Winter - weather: Sunny / Cloudy / Rainy / Stormy / Snowy / Foggy / Windy - duration: Brief / Short / Medium / Long / Extended / Ongoing For LLM-style timeframe extraction with narrative/temporal reasoning, use TIMEFRAME_LLM — see timeframe_dimension_llm.cascade.yaml.

Examples

Timeframe extracted

SELECT
  timeframe ('Expected to launch next quarter')

Nearby rabbit holes

same domain
dimension

AUDIENCE

Identify target audience via zero-shot NLI

classificationnlispecialist-zootext+1
dimension

AUDIENCE_LLM

LLM-backed audience identification (escape hatch for AUDIENCE)

classificationllmllm-escape-hatchtext
dimension

AUTHENTICITY

Assess authenticity of content via zero-shot NLI

classificationnlispecialist-zootext
dimension

AUTHENTICITY_LLM

LLM-backed authenticity assessment (escape hatch for AUTHENTICITY)

classificationllmllm-escape-hatchtext
dimension

BUCKET

Classify text into user-specified buckets via zero-shot NLI

classificationnlispecialist-zootext
dimension

BUCKET_LLM

LLM-backed bucketing (escape hatch for BUCKET)

classificationllmllm-escape-hatchtext
Climb back to The Looking Glass