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/separation-of-trades.md

@@ -0,0 +1,30 @@
+# Separation of Trades
+
+## Definition
+
+The process by which distinct occupations emerge as separate specialisations,
+each performed by dedicated practitioners rather than by a single person who
+performs all tasks. Smith presents the separation of trades as both a
+consequence and an indicator of the division of labour, noting that it
+advances furthest in the most industrious and improved countries.
+
+## Source Chapter
+
+Book I, Chapter 1: "Of the Division of Labour"
+
+## Context
+
+Smith transitions from the pin-factory example to the economy-wide observation
+that in improved societies, "the farmer is generally nothing but a farmer; the
+manufacturer, nothing but a manufacturer." He contrasts manufacturing, where
+trades separate extensively, with agriculture, where seasonal demands prevent
+full separation.
+
+## Economic Domain
+
+Production
+
+## Smith's Original Wording
+
+"The separation of different trades and employments from one another, seems to
+have taken place in consequence of this advantage."