Edit Step4_question_emergence Template

Step4_question_emergence v3

Viewer

Test Case:

Template

Preview

History

System prompt (optional) User prompt (template)

Analyze WHY each ethical question emerged using Toulmin's model.

{{ toulmin_context }}

## QUESTIONS TO ANALYZE
{{ questions_text }}

## EXTRACTED ENTITIES
{{ entities_text }}

For EACH question, use exact entity labels from the list above. Output JSON:
```json
[
  {
    "question_index": 1,
    "data_events": ["event label", ...],
    "data_actions": ["action label", ...],
    "involves_roles": ["role label", ...],
    "competing_warrants": [["obligation A label", "obligation B label"]],
    "data_warrant_tension": "1 sentence on how data triggers multiple warrants",
    "competing_claims": "1 sentence on what different warrants conclude",
    "rebuttal_conditions": "1 sentence on what creates uncertainty",
    "emergence_narrative": "1-2 sentences explaining why this question arose",
    "confidence": 0.8
  }
]
```

Include all questions in this batch.

{{ style_formatting_line }}

Loading preview...

Version History

No version history yet. Save changes to create versions.

Saved

897 chars

Reference

Template Variables

Shared ProEthica no-em-dash output formatting clause

Batch questions numbered Q1..Qn as 'Qn. label: text' lines

Concise Toulmin argumentation framing (DATA/WARRANT/REBUTTAL); empty string when the academic-references module is unavailable

Entity subgraph: nodes with definitions plus committed fulfills/violates/guided-by edges in label form

Output Schema

type array

items

JSON Wrapper

Appended to the prompt by the extractor:

IMPORTANT: Wrap your response as a JSON object with exactly two keys:
{"new_step4_question_emergence_classes": [...], "step4_question_emergence_individuals": [...]}
If there are no individuals to report, use an empty array for "step4_question_emergence_individuals".