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/saving-of-time.md

@@ -0,0 +1,30 @@
+# Saving of Time
+
+## Definition
+
+The elimination of time lost when a worker passes from one kind of work to
+another. Smith identifies this as the second mechanism by which the division of
+labour increases productive power. Time is lost both in physical transition
+(moving between locations and tools) and in mental transition (the sauntering
+and inattention that follows switching tasks).
+
+## Source Chapter
+
+Book I, Chapter 1: "Of the Division of Labour"
+
+## Context
+
+Presented as the second of three mechanisms. Smith argues the loss is greater
+than commonly supposed, encompassing not only travel time but a psychological
+cost: workers who constantly switch tasks develop habits of "sauntering" and
+"indolent careless application" that reduce their output even during active work.
+
+## Economic Domain
+
+Production
+
+## Smith's Original Wording
+
+"Secondly, the advantage which is gained by saving the time commonly lost in
+passing from one sort of work to another, is much greater than we should at
+first view be apt to imagine it."