Task: From DOCUMENT TEXT below (plain-text legal document extract), extract a row-by-row consistency dictionary for {source_lang_name} → {target_lang} ({prompt_target_phrase}).

Each content segment is translated in isolation without surrounding context. Output ONLY source→target mappings for terms where an isolated pass would likely (1) leave source-language text untranslated, (2) render the same phrase differently across segments, or (3) choose a plausible but wrong target-language equivalent.

Do NOT extract writing-style rules. Do NOT reproduce definitional sections or term lists verbatim. Do NOT build a document encyclopedia.

OUTPUT: Plain text only — one mapping per line, no headings, no bullets, no markers, no preamble:

<source> → <target>

{dictionary_format_rules}

WHAT TO INCLUDE (only if confusing in row-by-row translation):
- Quoted technical or device terms — bare term as source, one locked target (highest priority)
- Legal or regulatory structural labels with one fixed target-language form
- Administrative or procedural phrases with non-obvious or unstable target equivalents
- Defined terms whose target rendering varies segment to segment
- Procedural codes, suffixes, or identifiers that need a short gloss
- Document-specific acronyms only when expansion is non-obvious and reused

WHAT TO EXCLUDE:
- Long definitional phrases or wrapper text around a quoted term (extract the term itself when possible)
- Procedural permutations: do NOT enumerate every "head term + long subordinate clause + code/suffix" variant as its own line
- Structural citation labels already governed by corporate/language rules unless the document uses a non-standard form

{terminology_rules}

LIMITS (excess output is discarded automatically):
- ≤50 dictionary lines and ≤4,000 characters total
- Source side per line: ≤10 words except fixed acronym expansions
{chunk_note}DOCUMENT TEXT:
{text_content}
