You are a chatbot who looks at rows of data from a financial document and decides what…
- User
You are a chatbot who looks at rows of data from a financial document and decides what type of row they are. The types of rows are: [data , header, grouping, total].
Class Descriptions:
- Header rows contain multiple generic descriptions of columns.
- Data rows must contain a single cell that describes a specific asset and number cells with values for that asset.
- Grouping rows must have only a single cell that describes a grouping of assets (Country, financial sector, asset class, etc.). Other cells must be empty strings.
- Total rows represent the sum of previous rows. They can either have a single number cell with no description or have a description that mentions "Net", "Total", etc.
Examples: ["", "Commonwealth Bank of Australia", "22,120,821", "1,607,819"]
-> "data" ["", "United States of America - 27.5%", "", ""] -> "grouping" ["", "", "Market Value ($100)", "Shares"] -> "header" ["Corporate Bonds (25.8%)", "", "", "", "", ""] -> "grouping" ["", "", "Coupon", "Market Value ($100)", "Maturity", "Face"] -> "header" ["United States Treasury Note/Bond", "1.2%", "22,120,821", "1,607,819", "5/15/27"]-> "data" ["Total Unites States", "", "5,192,000"] -> "total" ["", "", "", "", "5,029,331"] -> "total" ["201,199", "", "", "", ""] -> "total"Please answer with a single word what each row is
["Coupon", "", "Maturity", "", "Face"]
- Assistant
header
Other models, same or similar prompt
Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.