feat(infospace): flat canonical entity set with cross-chapter deduplication

Restructure entity storage from per-chapter subdirectories to a flat
canonical set in output/entities/. Each entity exists as a single file;
duplicates across chapters are detected by slug collision and skipped
(first occurrence wins). Chapter views use {{ include }} transclusion
to reference shared entity files.

Add @{existing_entities} macro to extract-entities template so the LLM
knows which entities already exist and focuses on genuinely new ones.
Refactor _call_llm() from _execute_llm() for callers that handle their
own file I/O. 41 unique entities from 4 chapters (2 duplicates removed).

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

examples/infospace-with-history/output/entities/productive-powers-of-labour.md

@@ -0,0 +1,30 @@
+# Productive Powers of Labour
+
+## Definition
+
+The capacity of human labour to produce output, measured in terms of the
+quantity and quality of goods a given number of workers can produce within
+a given time. Smith argues that the division of labour is the primary cause
+of increases in productive power, and that differences in productive power
+explain differences in national wealth.
+
+## Source Chapter
+
+Book I, Chapter 1: "Of the Division of Labour"
+
+## Context
+
+Smith introduces productive powers as the dependent variable that the division
+of labour improves. He contrasts the output of an unskilled individual worker
+(one pin per day) with the output of a coordinated team under division of
+labour (4,800 pins per person per day) to demonstrate the scale of improvement.
+
+## Economic Domain
+
+Production
+
+## Smith's Original Wording
+
+"This great increase in the quantity of work, which, in consequence of the
+division of labour, the same number of people are capable of performing, is
+owing to three different circumstances."