update

templates/Prompt/Blocks-Dedup.md

@@ -0,0 +1,29 @@
+The FINAL block inventory for the topic "{topic}" was assembled from several sources. Despite earlier filtering it can still carry duplicates: the same concept listed under two names. For EACH pair below, decide: do A and B denote the SAME block → **ja**, or TWO DIFFERENT blocks → **nein**?
+
+THE MOST COMMON ERROR is merging a named VARIANT with its base entity. A variant is NEVER its base: "3-X" ≠ "X", "Max-X" ≠ "Max-3-X", "Modified X" ≠ "X", "k-X" ≠ "X". A digit or qualifier prefix that restricts the entity makes it a DIFFERENT entity → **nein**.
+
+PAIRS:
+{pairs}
+
+## How to decide (per pair)
+**STEP 1 — Name the CANONICAL ENTITY of each side.** Strip catalogue/reference additions („Definition 6.19", „Satz 7.8", „Kapitel 3"), parenthesized qualifiers that only restate or explain the name („X (full spelling)", „X (Problem)", „X-Problem"), spelling/spacing/hyphenation variants, translations of the same name, and genitive/apostrophe variants. „X" and „X (long form of X)" share one canonical entity.
+
+**STEP 2 — Same entity, or different?**
+- **SAME canonical entity → ja**, even when A and B emphasize DIFFERENT FACETS: formal definition vs. property vs. mechanism vs. characterization vs. naming variant. Two blocks about the same entity from different sources are duplicates.
+- **DIFFERENT canonical entity → nein**, however similar the wording:
+  - a named **variant, special case or modification** is its own entity („X" ≠ „Modified X", „3-X" ≠ „X");
+  - a **relation between two entities** (reduction, implication, comparison, mapping) is individuated by BOTH operands AND the direction. Same words, swapped direction → DIFFERENT. One shared operand, other operand differs → DIFFERENT. A relation is never a duplicate of one of its operands.
+  - a different parameter, restriction or scope is a different entity.
+
+**STEP 3 — „When in doubt → nein"** applies only when STEP 1 is genuinely ambiguous. Differing descriptions of the same entity are still **ja**.
+
+## Examples (example domain: graph theory — the rules hold for any topic)
+- A: „SAT" B: „SAT (Satisfiability Problem)" → same entity, naming only → **ja**
+- A: „P (Definition 6.20)" B: „P (Polynomialzeit)" → both = class **P**, definition vs. characterization → **ja**
+- A: „Hamiltonian Cycle ≤ Hamiltonian Path" B: „Hamiltonian Path ≤ Hamiltonian Cycle" → same words, opposite direction → **nein**
+- A: „Greedy-Algorithmus" B: „Modifizierter Greedy-Algorithmus" → base vs. named variant → **nein**
+
+Write ONLY the JSON file to: {out_path}
+
+Format (each pair number from the list with „ja" or „nein"; no other text in the file):
+{{"pairs": {{"1": "ja", "2": "nein"}}}}