PDF Document
Extracted Data
Comparison
Fields
Raw Text
Prompts
Schema
LLM Extracted Data
{
"companyName": "Greenfelder - Pollich",
"currency": "USD",
"preparedBy": {
"name": "Kent Kuphal-O'Keefe"
},
"reportType": "quarterly_report",
"reportingPeriod": {
"endDate": "2026-12-31",
"startDate": "2026-01-01"
},
"title": "2026 ANNUAL FINANCIAL REPORT"
}
Side-by-Side Comparison
Extracted
{
"companyName": "Greenfelder - Pollich",
"currency": "USD",
"preparedBy": {
"name": "Kent Kuphal-O'Keefe"
},
"reportType": "quarterly_report",
"reportingPeriod": {
"endDate": "2026-12-31",
"startDate": "2026-01-01"
},
"title": "2026 ANNUAL FINANCIAL REPORT"
}
Ground Truth
{
"approvedBy": {
"email": "Grant.Rippin@hotmail.com",
"name": "Dr. Noah Stokes",
"title": "National Research Strategist"
},
"balanceSheet": {
"assets": [
{
"items": [
{
"currentPeriod": 3225801,
"label": "Cash and Cash Equivalents"
},
{
"currentPeriod": 1443482,
"label": "Accounts Receivable"
},
{
"currentPeriod": 2990285,
"label": "Inventory"
}
],
"title": "Current Assets",
"total": 4267732
}
],
"equity": [
{
"items": [
{
"currentPeriod": 129675,
"label": "Common Stock"
},
{
"currentPeriod": 14240748,
"label": "Retained Earnings"
}
],
"title": "Shareholders' Equity",
"total": 14740748
}
],
"liabilities": [
{
"items": [
{
"currentPeriod": 562352,
"label": "Accounts Payable"
},
{
"currentPeriod": 480430,
"label": "Short-term Debt"
}
],
"title": "Current Liabilities",
"total": 4134383
}
]
},
"category": "report",
"companyName": "Greenfelder - Pollich",
"currency": "USD",
"documentId": "report-001-en",
"executiveSummary": "Somnus clamo capio creo demonstro venio calco cum sono. Vulgo necessitatibus aspicio defluo condico deserunt volutabrum bos molestias anser. Corrigo ulterius chirographum voluptas aggredior tolero deporto clamo cetera vere.\nConqueror adipiscor territo tertius similique. Chirographum vespillo voluptas decor. Congregatio texo verbum vigor tam arto cena.",
"financialHighlights": [
{
"change": 7.4,
"metric": "Total Revenue",
"value": 41663839
},
{
"change": -13.7,
"metric": "Net Income",
"value": 23180547
},
{
"change": -3.6,
"metric": "Total Assets",
"value": 18875131
}
],
"incomeStatement": {
"expenses": [
{
"currentPeriod": 9241646,
"label": "Cost of Goods Sold"
},
{
"currentPeriod": 5544987.6,
"label": "Operating Expenses"
},
{
"currentPeriod": 3696658.4000000004,
"label": "Administrative Expenses"
}
],
"netIncome": 23180547,
"revenue": [
{
"currentPeriod": 29164687.299999997,
"label": "Product Revenue"
},
{
"currentPeriod": 12499151.7,
"label": "Service Revenue"
}
]
},
"notes": [
{
"content": "Deficio casus cattus delibero trado sodalitas crux. Clam delinquo aliquam vigilo. Victoria careo adstringo demo.",
"number": 1,
"title": "synthesize revolutionary mindshare"
},
{
"content": "Comitatus compello vilis earum vobis somniculosus comburo. Consuasor adfero tenetur. Aestivus sodalitas tredecim verbum.",
"number": 2,
"title": "mesh rich schemas"
},
{
"content": "Sopor bonus statua. Circumvenio clam vorago addo vilicus tamquam patria. Atavus conservo usque anser spoliatio volaticus tenuis eveniet terreo.",
"number": 3,
"title": "mesh customized e-commerce"
}
],
"preparedBy": {
"email": "Newell89@gmail.com",
"name": "Kent Kuphal-O'Keefe",
"title": "Internal Operations Agent"
},
"reportType": "quarterly_report",
"reportingPeriod": {
"endDate": "2026-12-31",
"startDate": "2026-01-01"
},
"templateVariant": "default",
"title": "2026 Annual Financial Report"
}
Field Analysis
Matched
7
Mismatched
0
Missing
63
Accuracy
10.0%
Missing 63
- ? financialHighlights[1].metric expected "Net Income"
- ? notes[1].content expected "Comitatus compello vilis earum vobis somniculosus ..."
- ? balanceSheet.liabilities[0].title expected "Current Liabilities"
- ? balanceSheet.equity[0].items[1].currentPeriod expected "1.4240748e+07"
- ? financialHighlights._length expected "3"
- ? financialHighlights[0].change expected "7.4"
- ? balanceSheet.assets._length expected "1"
- ? financialHighlights[1].value expected "2.3180547e+07"
- ? financialHighlights[1].change expected "-13.7"
- ? financialHighlights[0].metric expected "Total Revenue"
- ? approvedBy.title expected "National Research Strategist"
- ? notes[2].title expected "mesh customized e-commerce"
- ? balanceSheet.equity[0].items._length expected "2"
- ? financialHighlights[2].change expected "-3.6"
- ? notes[2].content expected "Sopor bonus statua. Circumvenio clam vorago addo v..."
- ? balanceSheet.assets[0].items[1].currentPeriod expected "1.443482e+06"
- ? balanceSheet.liabilities[0].items[1].currentPeriod expected "480430"
- ? balanceSheet.equity[0].items[0].label expected "Common Stock"
- ? incomeStatement.expenses[2].label expected "Administrative Expenses"
- ? incomeStatement.expenses[2].currentPeriod expected "3.6966584000000004e+06"
- ? incomeStatement.revenue[0].label expected "Product Revenue"
- ? balanceSheet.assets[0].items[0].label expected "Cash and Cash Equivalents"
- ? incomeStatement.revenue[1].label expected "Service Revenue"
- ? notes[1].number expected "2"
- ? balanceSheet.assets[0].items[2].label expected "Inventory"
- ? balanceSheet.equity[0].total expected "1.4740748e+07"
- ? financialHighlights[2].metric expected "Total Assets"
- ? balanceSheet.liabilities[0].items._length expected "2"
- ? balanceSheet.assets[0].total expected "4.267732e+06"
- ? incomeStatement.revenue._length expected "2"
- ? incomeStatement.expenses[1].currentPeriod expected "5.5449876e+06"
- ? incomeStatement.expenses[0].label expected "Cost of Goods Sold"
- ? balanceSheet.equity[0].items[1].label expected "Retained Earnings"
- ? notes._length expected "3"
- ? balanceSheet.assets[0].items._length expected "3"
- ? balanceSheet.liabilities[0].items[0].currentPeriod expected "562352"
- ? balanceSheet.equity._length expected "1"
- ? executiveSummary expected "Somnus clamo capio creo demonstro venio calco cum ..."
- ? balanceSheet.liabilities[0].items[0].label expected "Accounts Payable"
- ? balanceSheet.liabilities[0].items[1].label expected "Short-term Debt"
- ? balanceSheet.liabilities[0].total expected "4.134383e+06"
- ? incomeStatement.expenses[1].label expected "Operating Expenses"
- ? notes[0].title expected "synthesize revolutionary mindshare"
- ? notes[2].number expected "3"
- ? balanceSheet.assets[0].items[0].currentPeriod expected "3.225801e+06"
- ? financialHighlights[2].value expected "1.8875131e+07"
- ? incomeStatement.revenue[0].currentPeriod expected "2.9164687299999997e+07"
- ? incomeStatement.netIncome expected "2.3180547e+07"
- ? incomeStatement.revenue[1].currentPeriod expected "1.24991517e+07"
- ? notes[0].content expected "Deficio casus cattus delibero trado sodalitas crux..."
- ? preparedBy.title expected "Internal Operations Agent"
- ? notes[0].number expected "1"
- ? balanceSheet.liabilities._length expected "1"
- ? balanceSheet.equity[0].items[0].currentPeriod expected "129675"
- ? notes[1].title expected "mesh rich schemas"
- ? balanceSheet.equity[0].title expected "Shareholders' Equity"
- ? balanceSheet.assets[0].title expected "Current Assets"
- ? balanceSheet.assets[0].items[1].label expected "Accounts Receivable"
- ? balanceSheet.assets[0].items[2].currentPeriod expected "2.990285e+06"
- ? incomeStatement.expenses._length expected "3"
- ? approvedBy.name expected "Dr. Noah Stokes"
- ? financialHighlights[0].value expected "4.1663839e+07"
- ? incomeStatement.expenses[0].currentPeriod expected "9.241646e+06"
Matched 7
- ✓ preparedBy.name
- ✓ companyName
- ✓ reportingPeriod.startDate
- ✓ title
- ✓ reportingPeriod.endDate
- ✓ reportType
- ✓ currency
Extracted Text from PDF
2026 ANNUAL FINANCIAL REPORT Company: Greenfelder - Pollich Report Type: QUARTERLY REPORT Period: 2026-01-01 to 2026-12-31 Currency: USD Prepared by: Kent Kuphal-O'Keefe Executive Summary Somnus clamo capio creo demonstro venio calco cum sono. Vulgo necessitatibus aspicio defluo condico deserunt volutabrum bos molestias anser. Corrigo ulterius chirographum voluptas aggredior tolero deporto clamo cetera vere. Conqueror adipiscor territo tertius similique. Chirographum vespillo voluptas decor. Congregatio texo verbum vigor tam arto cena. Financial Highlights • Total Revenue: USD 41,663,839 (+7.4%) • Net Income: USD 23,180,547 (-13.7%) • Total Assets: USD 18,875,131 (-3.6%) Income Statement Revenue: Product Revenue: USD 29,164,687.3 Service Revenue: USD 12,499,151.7 Expenses: Cost of Goods Sold: USD 9,241,646 Operating Expenses: USD 5,544,987.6 Administrative Expenses: USD 3,696,658.4 Net Income: USD 23,180,547
System Prompt
You are a precise document data extraction expert. Your task is to extract structured data from report documents. ## Extraction Guidelines Extract report data including: - Report type, title, company name - Reporting period (start/end dates) - Currency, prepared by, approved by - Executive summary - Financial highlights - Balance sheet and income statement data ## Important Rules 1. **Dates**: Always use ISO format (YYYY-MM-DD) for full dates, HH:MM for times 2. **Currency**: Use 3-letter ISO 4217 codes (EUR, USD, GBP, etc.) 3. **Missing optional fields**: Omit them entirely, don't use null or empty strings 4. **Required fields**: Make your best effort to extract; if truly not present, use reasonable placeholder 5. **Numbers**: Extract as numeric values, not strings (except for identifiers like document numbers) 6. **Arrays**: Always return arrays even if only one item exists 7. **Text content**: Preserve important content accurately but you may summarize very long passages 8. **Names**: Extract full names as they appear in the document Respond with a JSON object containing the extracted data. Be precise and extract only what is explicitly stated in the document.
User Prompt
Please extract all structured data from this report document: --- 2026 ANNUAL FINANCIAL REPORT Company: Greenfelder - Pollich Report Type: QUARTERLY REPORT Period: 2026-01-01 to 2026-12-31 Currency: USD Prepared by: Kent Kuphal-O'Keefe Executive Summary Somnus clamo capio creo demonstro venio calco cum sono. Vulgo necessitatibus aspicio defluo condico deserunt volutabrum bos molestias anser. Corrigo ulterius chirographum voluptas aggredior tolero deporto clamo cetera vere. Conqueror adipiscor territo tertius similique. Chirographum vespillo voluptas decor. Congregatio texo verbum vigor tam arto cena. Financial Highlights • Total Revenue: USD 41,663,839 (+7.4%) • Net Income: USD 23,180,547 (-13.7%) • Total Assets: USD 18,875,131 (-3.6%) Income Statement Revenue: Product Revenue: USD 29,164,687.3 Service Revenue: USD 12,499,151.7 Expenses: Cost of Goods Sold: USD 9,241,646 Operating Expenses: USD 5,544,987.6 Administrative Expenses: USD 3,696,658.4 Net Income: USD 23,180,547 --- Extract the data as JSON according to the schema.
Raw LLM Response
{
"reportType": "quarterly_report",
"title": "2026 ANNUAL FINANCIAL REPORT",
"companyName": "Greenfelder - Pollich",
"reportingPeriod": {
"startDate": "2026-01-01",
"endDate": "2026-12-31"
},
"currency": "USD",
"preparedBy": {
"name": "Kent Kuphal-O'Keefe"
}
}
JSON Schema (Structured Output)
This schema is passed to the LLM via ResponseSchema
to enforce structured JSON output.
{
"example": {
"approvedBy": {
"name": "Michael Brown",
"title": "Chief Financial Officer"
},
"balanceSheet": {
"assets": [
{
"name": "Cash and Equivalents",
"value": 2000000
},
{
"name": "Accounts Receivable",
"value": 1500000
}
],
"equity": [
{
"name": "Common Stock",
"value": 1000000
},
{
"name": "Retained Earnings",
"value": 1000000
}
],
"liabilities": [
{
"name": "Accounts Payable",
"value": 500000
},
{
"name": "Long-term Debt",
"value": 1000000
}
]
},
"companyName": "Global Industries Ltd.",
"currency": "USD",
"executiveSummary": "Q1 2024 showed strong revenue growth of 15% year-over-year with improved operational efficiency.",
"financialHighlights": [
{
"changePercentage": 15,
"metric": "Revenue",
"value": 5000000
},
{
"changePercentage": 12.5,
"metric": "Net Income",
"value": 750000
}
],
"preparedBy": {
"name": "Jennifer Adams",
"title": "Financial Controller"
},
"reportType": "quarterly_report",
"reportingPeriod": {
"endDate": "2024-03-31",
"startDate": "2024-01-01"
},
"title": "Q1 2024 Financial Report"
},
"properties": {
"approvedBy": {
"properties": {
"email": {
"description": "Email address",
"type": "STRING"
},
"name": {
"description": "Full name of the person",
"type": "STRING"
},
"title": {
"description": "Job title or role",
"type": "STRING"
}
},
"required": [
"name"
],
"type": "OBJECT"
},
"balanceSheet": {
"properties": {
"assets": {
"items": {
"properties": {
"name": {
"type": "STRING"
},
"value": {
"type": "NUMBER"
}
},
"type": "OBJECT"
},
"type": "ARRAY"
},
"equity": {
"items": {
"properties": {
"name": {
"type": "STRING"
},
"value": {
"type": "NUMBER"
}
},
"type": "OBJECT"
},
"type": "ARRAY"
},
"liabilities": {
"items": {
"properties": {
"name": {
"type": "STRING"
},
"value": {
"type": "NUMBER"
}
},
"type": "OBJECT"
},
"type": "ARRAY"
}
},
"type": "OBJECT"
},
"companyName": {
"type": "STRING"
},
"currency": {
"description": "3-letter ISO currency code",
"type": "STRING"
},
"executiveSummary": {
"type": "STRING"
},
"financialHighlights": {
"items": {
"properties": {
"changePercentage": {
"type": "NUMBER"
},
"metric": {
"type": "STRING"
},
"value": {
"type": "NUMBER"
}
},
"required": [
"metric",
"value"
],
"type": "OBJECT"
},
"type": "ARRAY"
},
"incomeStatement": {
"properties": {
"expenses": {
"items": {
"properties": {
"name": {
"type": "STRING"
},
"value": {
"type": "NUMBER"
}
},
"type": "OBJECT"
},
"type": "ARRAY"
},
"netIncome": {
"type": "NUMBER"
},
"revenue": {
"items": {
"properties": {
"name": {
"type": "STRING"
},
"value": {
"type": "NUMBER"
}
},
"type": "OBJECT"
},
"type": "ARRAY"
}
},
"type": "OBJECT"
},
"notes": {
"items": {
"properties": {
"content": {
"type": "STRING"
},
"number": {
"type": "STRING"
},
"title": {
"type": "STRING"
}
},
"type": "OBJECT"
},
"type": "ARRAY"
},
"preparedBy": {
"properties": {
"email": {
"description": "Email address",
"type": "STRING"
},
"name": {
"description": "Full name of the person",
"type": "STRING"
},
"title": {
"description": "Job title or role",
"type": "STRING"
}
},
"required": [
"name"
],
"type": "OBJECT"
},
"reportType": {
"enum": [
"annual_report",
"quarterly_report",
"financial_statement",
"audit_report",
"board_report"
],
"type": "STRING"
},
"reportingPeriod": {
"properties": {
"endDate": {
"description": "Date in YYYY-MM-DD format",
"type": "STRING"
},
"startDate": {
"description": "Date in YYYY-MM-DD format",
"type": "STRING"
}
},
"required": [
"startDate",
"endDate"
],
"type": "OBJECT"
},
"title": {
"type": "STRING"
}
},
"required": [
"reportType",
"title",
"companyName",
"reportingPeriod"
],
"type": "OBJECT"
}