fix(example): standardise domain enum and source chapter format in schema/rules
Two root causes of metric fragmentation observed in collection checks:
1. Schema's Economic Domain used free-form examples ("labour economics,
trade theory") which overrode the enum in extraction-rules.md, causing
the LLM to produce multi-domain strings and non-canonical values.
Fix: schema now specifies the exact 7-value enum with descriptions.
2. Source Chapter had no format constraint, producing 9 different formats
for 7 chapters (full titles, mixed Roman/Arabic numerals, asterisks).
Fix: extraction-rules now mandate "Book [Roman], Chapter [n]" exactly.
These fixes are prerequisites for clean reprocessing (S3.2 continuation).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -57,5 +57,10 @@ entities at the level of specificity where they carry independent meaning.
|
||||
- Each entity must have a definition that would be comprehensible without
|
||||
reading the source chapter.
|
||||
- Each entity must cite the specific book and chapter of first appearance.
|
||||
- Economic Domain must be one of: Production, Distribution, Exchange,
|
||||
Consumption, Accumulation, Regulation, or General Theory.
|
||||
- **Economic Domain** must be EXACTLY ONE of: Production, Distribution,
|
||||
Exchange, Consumption, Accumulation, Regulation, or General Theory.
|
||||
Do not combine multiple domains. Do not use any other value.
|
||||
- **Source Chapter format**: Use `Book [Roman numeral], Chapter [number]`
|
||||
— for example `Book I, Chapter 3`. Do not include the chapter title,
|
||||
quotation marks, markdown formatting, or asterisks. Use Roman numerals
|
||||
for the book (I, II, III, IV, V).
|
||||
|
||||
Reference in New Issue
Block a user