I have a list of ingredients that I would like to format in a simple and consistent way,…
- User
I have a list of ingredients that I would like to format in a simple and consistent way, following this structure:
"Quantity Unit Description."
Formatting Rules:
Quantity must be a number (e.g., "200" instead of "two hundred").
Unit must use the metric system and the corresponding abbreviated form (e.g., grams → g, liters → l, milliliters → ml, etc.).
Description should be the ingredient, including any specific details if mentioned (e.g., "brown sugar", "melted unsalted butter").
If an ingredient is already formatted correctly, do not change it.
Do not invent a quantity or unit if none is provided — leave it as is and just include the description.
If a line includes alternatives or multiple options (e.g., a frozen or canned version), it should remain as a single line in the output and not be split into separate ingredients.
Return Format: The result should be returned as a properly formatted JSON object, like this: json { "data": } Please reformat each ingredient in the list I will provide according to these guidelines.
Context Dump Ingredients source provided: 24 oz. chicken breasts, cut into chunks and sautéed,1 C. green pepper, cleaned and sliced into strips,1 C. red pepper, cleaned and sliced into strips,1 C. onion, cleaned and sliced into strips,1/2 C. zucchini, sliced (optional),1 garlic clove, minced,2 tbsps parsley, chopped,1 (16 oz.) can stewed tomatoes with juice,5 tbsps olive oil,1 tsp Arabic seven spice,1/2 tsp salt and pepper
- Assistant
{ "data": [ "680 g chicken breasts, cut into chunks and sautéed.", "240 ml green pepper, cleaned and sliced into strips.", "240 ml red pepper, cleaned and sliced into strips.", "240 ml onion, cleaned and sliced into strips.", "120 ml zucchini, sliced (optional).", "1 garlic clove, minced.", "2 tbsp parsley, chopped.", "1 (454 g) can stewed tomatoes with juice.", "5 tbsp olive oil.", "1 tsp Arabic seven spice.", "1/2 tsp salt and pepper." ] }
Other models, same or similar prompt
Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.