You are given ONE film-still description, its location text, and the
world facts. Decide whether the scene ITSELF names writing that must be
readable in frame, and when it does, author the exact words — because
the image model receives only what you write here and must not invent
lettering on its own.

Ground every entry in what you were given, say where it came from, and
**quote the exact words you are grounding it on**:

- scene_text_quoted — the SHOT text spells out the words themselves. The
  words you write MUST appear inside the quote you give.
- scene_text_implied — the SHOT text names something meant to be read, or
  names someone reading, but never says what it says. The object is
  there; the wording is not.
- world_facts — the world facts spell out these words for this place and
  era. Same rule as scene_text_quoted: the words must be inside the quote.
- inferred — none of the above. You reasoned it from what kind of place
  this is, or from what would plausibly be there.

The LOCATION text is context, not a source: it describes what kind of
place this is, and "this kind of place would carry such writing" is a
guess, not grounding.

The quote is checked against the text you were given. Copy it, do not
paraphrase it, do not tidy it — a stretch of characters that appears
there exactly as written. If you cannot find such a stretch, the entry is
`inferred` and the quote is empty; say so honestly rather than reaching
for something close.

★ Do not translate or rephrase to make the words fit. If the shot says
someone reads something meant to be read but never gives its wording,
that is `scene_text_implied` — not `scene_text_quoted` with a word you
supplied.

Be honest about `inferred`. A plausible guess is still a guess, and
"this would make the place read as itself" is exactly a guess. Most film
stills name no writing at all — an ordinary room, street, or vehicle
carries none the scene calls for. When the scene names nothing, return
an empty list. That is the expected answer, not a failure.

Do not choose where the writing goes. Name only the words; the image
already establishes the surfaces.

Never write dialogue, captions, subtitles, or narration. Never use real
brand names, real institutions, or personal names unless the scene text
itself names them.

Return for each entry:

- text_native: the exact words, in the NATIVE language and script of the
  place and era the world facts establish — never another language,
  never romanization. Short, and worded the way it would actually be
  written there and then.
- source: scene_text_quoted, scene_text_implied, world_facts, or
  inferred, as defined above.
- source_quote: for the first three, the stretch copied from the given
  text. For inferred, an empty string.
- reason_ko: 한 문장 — 무엇이 이 글자를 부르는가.