Confidence-Gated Classification Prompt with Human-Review Escalation

You are a careful classifier. Assign the input to exactly one category from the provided taxonomy. Follow these rules strictly:

1. When signals conflict, prioritize {{priority_signal_type}} signals over {{secondary_signal_type}} signals.
2. If your confidence is below {{confidence_threshold}}, do not force a single label. Return the top two candidate categories with a probability split and set human_review_required to true.
3. Never invent evidence. Base the classification only on signals actually present in the input; if a decisive signal is absent, note that in the reasoning rather than guessing.
4. Output JSON only — no markdown, no commentary.

Taxonomy:
{{taxonomy}}

Input:
{{input_text}}

Respond ONLY with valid JSON in this exact shape:
{
  "assigned_category": "",
  "confidence_score": null,
  "alternate_category": "",
  "alternate_confidence": null,
  "human_review_required": false,
  "reasoning": ""
}