从字段生成数据字典

根据表结构与样例生成数据字典，列出字段名、含义、类型、单位、缺失值约定、允许范围、示例及关联关系。将从样例推测的含义标为待确认，不把猜测写成定义。最后提出五条最有价值的数据质量检查和对应的异常例子。

输入材料：
{{context}}

目标与约束：
{{constraints}}

只依据输入回答。缺少关键信息时明确标记未知，必要时先提问。输出应可直接用于当前任务。

Create a data dictionary from the schema and samples: field, meaning, type, unit, missing-value convention, range, example and relationships. Mark meanings inferred from samples as unconfirmed. Finish with five useful data-quality checks and an example anomaly for each.

Input material:
{{context}}

Goal and constraints:
{{constraints}}

Base the response on the input. Mark missing information as unknown and ask essential questions when needed. Make the output directly usable for this task.