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: ½ pound boneless, skinless chicken breast, cut into 1-inch pieces,1 tablespoon finely minced garlic,1 tablespoon finely minced fresh ginger,2 tablespoons freshly squeezed lime juice, divided,1 tablespoon vegetable oil,2 medium red onions, minced,1½ teaspoons kosher salt,¼ teaspoon ground cinnamon,¼ teaspoon ground black pepper,1 serrano chile, seeded and minced,2 tablespoons minced fresh cilantro
- Assistant
{ "data": [ "227 g boneless, skinless chicken breast, cut into 1-inch pieces.", "15 ml finely minced garlic.", "15 ml finely minced fresh ginger.", "30 ml freshly squeezed lime juice, divided.", "15 ml vegetable oil.", "2 medium red onions, minced.", "7.5 ml kosher salt.", "0.25 ml ground cinnamon.", "0.25 ml ground black pepper.", "1 serrano chile, seeded and minced.", "30 ml minced fresh cilantro." ] }
Other models, same or similar prompt
Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.