surface↓classification↓narrative
Classificationdimension · returns varchar

NARRATIVE

Identify narrative frame via zero-shot NLI

Per-row classifier — stable across GROUP BY.

classificationnlispecialist-zootext

Arguments

nametypedescription
textVARCHAR—
contextVARCHAR—

About

Narrative frame analyzer — identifies which story structure an author is using. Useful for media analysis and rhetoric studies. Backend: specialist zoo zero-shot NLI via /classify_batch. Default frame labels are 10 common narrative structures. Optional `context` argument steers the hypothesis template (e.g., context='election' → "In the context of elections, this text frames events as: ..."). For LLM-style frame identification with domain-specific rhetoric knowledge, use NARRATIVE_LLM — see narrative_dimension_llm.cascade.yaml.

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