> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/juanceresa/sift-kg/llms.txt
> Use this file to discover all available pages before exploring further.

# Epstein/Maxwell Deposition Example

> Knowledge graph from unsealed Giuffre v. Maxwell court deposition with OCR support

Complete sift-kg pipeline output from the unsealed Giuffre v. Maxwell court deposition, demonstrating OCR extraction from a scanned PDF and producing a graph of **190 entities** and **387 relations**.

## Overview

This example demonstrates knowledge graph extraction from legal documents with OCR-scanned content, showing how sift-kg handles complex PDFs where text must be extracted via optical character recognition.

<CardGroup cols={2}>
  <Card title="View Interactive Graph" icon="diagram-project">
    Open `examples/epstein/output/graph.html` in your browser
  </Card>

  <Card title="Source Document" icon="file-pdf">
    1 PDF with 36 sections (unsealed court deposition)
  </Card>
</CardGroup>

## Quick Start

```bash theme={null}
# View the interactive graph (no installation needed)
open examples/epstein/output/graph.html     # macOS
xdg-open examples/epstein/output/graph.html # Linux

# Or use sift's built-in viewer
sift view -o examples/epstein/output
```

## Pipeline Output

The `output/` directory contains the complete pipeline results:

```
epstein/
├── docs/                          # Source PDF (unsealed court deposition)
└── output/
    ├── extractions/               # Per-document entity+relation JSON from LLM
    ├── graph_data.json            # Knowledge graph (226 entities, 708 relations)
    ├── merge_proposals.yaml       # Entity merge decisions (16 confirmed merges)
    ├── relation_review.yaml       # Flagged relations reviewed
    ├── communities.json           # Detected graph communities
    ├── entity_descriptions.json   # AI-generated entity descriptions
    ├── narrative.md               # Prose narrative with entity profiles
    └── graph.html                 # Interactive pyvis graph viewer
```

## Pipeline Statistics

| Metric               | Value                                                             |
| -------------------- | ----------------------------------------------------------------- |
| **Input Document**   | 1 PDF, 36 sections                                                |
| **Document Type**    | Unsealed court deposition (OCR-scanned)                           |
| **Initial Entities** | 226 entities, 708 relations (after build + postprocess)           |
| **Entity Types**     | 93 persons, 56 locations, 24 organizations, 15 events, 2 vehicles |
| **After Resolution** | 190 entities, 387 relations (16 entity merges confirmed)          |
| **Model Used**       | claude-haiku-4-5-20251001                                         |

## OCR Processing

This example requires the `--ocr` flag during extraction to handle scanned PDFs:

```bash theme={null}
sift extract examples/epstein/docs --model openai/gpt-4o-mini -o my-output --ocr
```

The `--ocr` flag:

* Uses optical character recognition to extract text from scanned images
* Handles PDFs where text is not digitally encoded
* Works with low-quality scans, handwritten documents, and mixed content
* Automatically falls back to OCR when native text extraction fails

<Warning>
  OCR processing may increase extraction time and cost. Ensure your documents actually require OCR before using this flag.
</Warning>

## Entity Types

The deposition primarily contains:

* **Persons** (93) — Named individuals mentioned in testimony
* **Locations** (56) — Places referenced in the deposition
* **Organizations** (24) — Companies, institutions, and groups
* **Events** (15) — Specific incidents and occasions
* **Vehicles** (2) — Named aircraft or vehicles

These entity types are automatically detected based on the content — no custom domain configuration was needed.

## Resolution and Review

This example includes:

### Entity Merges

16 entity merges were confirmed via `sift resolve` and human review:

```yaml theme={null}
merges:
  - primary: "Jeffrey Epstein"
    duplicates:
      - "Epstein"
      - "Mr. Epstein"
    status: CONFIRMED
```

### Relation Review

The `relation_review.yaml` file contains flagged relations that were reviewed for accuracy:

```yaml theme={null}
relations:
  - source: "Person A"
    target: "Location B"
    relation_type: "VISITED"
    status: CONFIRMED
    notes: "Explicitly stated in testimony"
```

This demonstrates sift-kg's support for reviewing potentially sensitive or ambiguous relationships.

## Key Insights from the Graph

The generated narrative (`narrative.md`) provides:

* **Overview** — High-level summary of testimony content
* **Entity descriptions** — AI-generated profiles for key persons, locations, and organizations
* **Community detection** — Clustered subgraphs showing relationship networks

<Note>
  This example demonstrates technical capabilities for processing legal documents. The content itself is a matter of public record from unsealed court proceedings.
</Note>

## Re-running the Example

### Option 1: Build from Existing Extractions (Free)

Use the pre-extracted entities — no LLM API calls:

```bash theme={null}
pip install sift-kg
sift build -o examples/epstein/output
sift view -o examples/epstein/output
```

### Option 2: Full Pipeline from Scratch

Re-extract entities from the source PDF with OCR:

```bash theme={null}
# Extract entities with OCR support
sift extract examples/epstein/docs \
  --model openai/gpt-4o-mini \
  -o my-output \
  --ocr

# Build the knowledge graph
sift build -o my-output

# Resolve duplicate entities
sift resolve -o my-output --model openai/gpt-4o-mini

# Review proposed merges
sift review -o my-output

# Apply confirmed merges
sift apply-merges -o my-output

# Generate narrative
sift narrate -o my-output --model openai/gpt-4o-mini

# View the result
sift view -o my-output
```

<Tip>
  Always use the `--ocr` flag when working with scanned documents, court filings, or any PDF where you cannot select and copy text.
</Tip>

## Use Cases

This example pattern works well for:

* **Legal discovery** — Map entities and relationships from depositions and court documents
* **Investigative research** — Extract structured data from public records
* **Historical archives** — Process scanned documents and old records
* **Due diligence** — Analyze legal filings and testimony

## Processing Scanned Documents

When working with OCR documents:

1. **Test OCR quality** — Preview extracted text to ensure readability
2. **Adjust models** — Consider using more powerful models (GPT-4) for complex layouts
3. **Review carefully** — OCR errors can propagate to entity extraction
4. **Use resolution** — Merge entities that may have OCR-induced variations

## Next Steps

<CardGroup cols={2}>
  <Card title="Explore Other Examples" icon="folder-open" href="/examples/overview">
    See Transformers and FTX examples
  </Card>

  <Card title="OCR Guide" icon="scanner" href="/guides/extraction">
    Learn more about processing scanned documents
  </Card>
</CardGroup>