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: 1 cup fine bulgur,2 teaspoons sweet or hot Turkish red pepper paste,2 teaspoons tomato paste,2 scallions, white and green parts, thinly sliced,1 packed cup finely chopped fresh flat-leaf parsley,½ packed cup finely chopped fresh mint,2 tablespoons plus 2 teaspoons pomegranate molasses, or to taste,1 tablespoon plus 2 teaspoons olive oil,1/4 teaspoon fine sea salt,Turkish or other crushed red pepper flakes (optional)
- Assistant
{ "data": [ "240 ml fine bulgur.", "10 ml sweet or hot Turkish red pepper paste.", "10 ml tomato paste.", "2 scallions, white and green parts, thinly sliced.", "240 ml finely chopped fresh flat-leaf parsley.", "120 ml finely chopped fresh mint.", "30 ml plus 10 ml pomegranate molasses, or to taste.", "15 ml plus 10 ml olive oil.", "1.25 ml fine sea salt.", "Turkish or other crushed red pepper flakes (optional)." ] }
Other models, same or similar prompt
Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.