You are an expert in data analysis and explainable artificial intelligence.
Your task is to analyze records from a dataset and discover interpretable,
human-understandable features that can differentiate between {n_classes} record categories:
{class_list}

Each record is shown to you as text describing its field values. You must reason from
these values themselves, without assuming any predefined feature types, and describe
the distinguishing properties as if explaining them to a human researcher.

I am providing you with example records. Each record belongs to one of the {n_classes} categories
listed above, but you are NOT told which record belongs to which category.

Do not use the category names or paraphrases of them as feature names or
values. Describe the property itself instead, in general terms rather than
names or phrases taken from the examples.

Your task is to:
  1. Examine all records carefully and propose key features that appear to
     systematically vary across subsets of the records and together distinguish all
     {n_classes} categories in a classification model.
  2. Focus on properties a domain expert would recognise: value ranges and their
     rough magnitude, combinations of fields that occur together, categorical
     patterns, presence or absence of information, or ratios between fields.
  3. Propose features that summarise or combine what the fields say. Do not simply
     restate a single column as a feature.
  4. Each feature must capture a different property. Do not propose two features
     that would almost always take related values.
  5. Some categories will resemble each other much more closely than others.
     Make sure the feature set also separates the closest pairs, not only the
     obvious groupings.
  6. Express each feature as a short snake_case attribute name.
  7. For each feature, provide a brief explanation of why it could be discriminative
     across the {n_classes} hidden groups.
  8. For each feature, provide 3-6 possible values: short snake_case strings
     without filler words, mutually exclusive, together covering the realistic
     range. If a feature cannot apply to some of the categories, include an
     explicit value for that case (for example not_applicable) in the list.
     These exact values will later be used to label new records, so choose
     values you can apply consistently.
  9. Provide at least {min_features} distinct features.
  10. Respond only with valid JSON. Do not wrap it in markdown code fences and do not include any explanation outside the JSON.

Output format:
{{
  "proposed_features": [
    {{
      "feature": "feature_name_1",
      "description": "why it separates the {n_classes} groups",
      "possible_values": ["value1", "value2", "value3"]
    }}
  ]
}}