1. Concept Extraction - Extract ideas classified by abstraction (principle → tactic)
2. Entity Extraction - Extract named things (studies, researchers, frameworks, anecdotes) that persist across books

• Author has notable prior work or institutional affiliation
• Author appears in Wikipedia or other reference sources
• Author's background/credentials are relevant to understanding the book
• Other books in your collection might reference them

• Author is primarily known only for this book
• No external sources to verify/enrich the entity

undefined

1. [Claim or finding with source] — Source: [Book], Ch.[X]
2. [Another claim] — Source: [Book], Ch.[X]

"Quotable text here."

"Another memorable quote."

• [Book that would enrich this entity]

• Other Entity - Relationship description

• [What we don't yet know]

undefined

"Quote text here."

"Another quote on same theme."

"Quote on different theme."

**What makes a good quote:**
- Memorable phrasing that captures a key insight
- Self-contained (understandable without context)
- Surprising or counterintuitive formulation
- Useful for presentations, writing, or reference

1. Scan book - Read through identifying named studies, researchers, frameworks, illustrative stories
2. Check existing entities - Use

   kb-resolve-entity.ts

   to see if entity already exists
3. Create or update - New entity → create file; existing → add as source
4. Add quotes - Extract memorable quotes to quotes file
5. Cross-link - Add Related Entities sections
6. Regenerate index - Run

   kb-generate-index.ts

1. Find entities that appear in multiple books
2. Identify conceptual connections between books
3. Surface contradictions or complementary perspectives
4. Update entity files with multi-source synthesis

1. Entity overlap detection
   bash

   # Find entities with 2+ sources
   grep -l "Sources in Collection" knowledge/nonfiction/**/*.md | \
     xargs grep -l "| .* | .* |" | head -20

   Or manually review entities updated with new source.
2. Conceptual connection mapping
   • Compare frameworks across books (e.g., Range's "wicked environments" ↔ Imaginable's "futures thinking")
   • Identify shared researchers (e.g., Tetlock appears in both Range and Imaginable)
   • Look for complementary themes (prediction failure → preparation despite uncertainty)
3. Synthesis documentation For entities appearing in 2+ books, update the Summary section:
   markdown

   ## Summary
   [Synthesized understanding from BOTH sources, noting agreements and differences]

4. Cross-book insights Document thematic connections in

   context/insights/cross-book-{theme}.md

   :
   markdown

   # Cross-Book Insight: [Theme]
   
   ## Books Contributing
   - Range (Epstein) - [perspective]
   - Imaginable (McGonigal) - [perspective]
   
   ## Synthesis
   [How the books complement or contradict each other]

1. Parse - Run

   ea-parse.ts

   to chunk book with position tracking
2. Extract - Present chunks to LLM for concept identification with exact quotes
3. Classify - Assign type (principle→tactic) and layer (0-4)
4. Annotate - Add themes and functional analysis
5. Link - Connect related concepts
6. Export - Generate analysis.json, concepts.json, report.md

deno run --allow-read scripts/kb-resolve-entity.ts "Flynn Effect"
deno run --allow-read scripts/kb-resolve-entity.ts "Hogarth" --threshold 0.5
deno run --allow-read scripts/kb-resolve-entity.ts "kind learning" --json

• --threshold <0-1>

  - Minimum match score (default: 0.3)

• --limit <n>

  - Maximum results (default: 5)

• --json

  - Output as JSON

• Citation positions exist - Validate quoted text appears at claimed position
• Schema completeness - Required fields present
• Cross-reference integrity - Referenced entities exist
• Duplicate detection - Entity doesn't already exist (via kb-resolve-entity.ts)

• Significance - Is this worth extracting?
• Classification - Is this really a "framework" vs "concept"?
• Relationship validity - Does A really influence B?
• Quote quality - Is this actually memorable?

• Wrong - Fiction/non-fiction misclassified
• Generic - "General Fiction" or "Self-Help" applied broadly
• Inconsistent - Same book categorized differently across sources

• Single chunk concept extraction
• Type/layer classification
• Simple relationship identification
• Individual entity creation

• Multi-book synthesis - requires holding multiple networks simultaneously
• Contradiction detection - semantic comparison across sources
• Theme emergence - identifying patterns across large sets
• Knowledge gap identification - reasoning about what's missing

• Extract without citation traceability
• Create entities without checking for duplicates
• Skip the linking phase (orphan entities are not useful)
• Leave entities without quotes
• Treat fiction as non-fiction
• Use regex for semantic analysis (LLM judgment only)