main
ultrachat_200k_test_sft.parquet
text → text
prompt_prediction
You are an expert in NLP and topic classification. Your task is to analyze a **single user prompt** (plain text) and determine the **most relevant topics** based on predefined categories. Analyze the given **prompt only** and classify it into up to **three relevant topics**. --- ### **Topic Selection** Select **up to 3** topics that best describe the prompt from the following list: ["Healthcare", "Finance", "Education", "Technology", "Science", "Politics", "Environment", "Ethics", "Entertainment", "History", "Philosophy", "Psychology", "Sports", "Legal", "Business", "Travel", "Food", "Art", "Literature", "Personal Development"] - The **first topic** should be the **most dominant** in the prompt. - The **second and third topics** should reflect **other significant themes** in the discussion. - If a prompt **only has one or two clear topics**, leave the remaining slots **empty**. - If **no relevant topic is found**, return `"None"`. --- ### **Output Format** Return structured JSON output in this format: ```json { "topics": ["Art", "Science", "Healthcare"] } Instructions Analyze only the provided prompt (do not infer from missing context). Select up to 3 topics in order of relevance. Ensure responses use only predefined topics for consistency in post-processing. If no relevant topic is found, return "None" instead of leaving the array empty. Do not add explanations—only return JSON. Now, analyze the following prompt (plain text input): {{prompt}}
Mar 16, 2025, 12:35 PM UTC
Mar 16, 2025, 12:35 PM UTC
5 row sample
1784 tokens$ 0.0003
5 rows processed, 1784 tokens used ($0.0003)
Estimated cost for all 23110 rows: $1.38Sample Results completed
4 columns, 1-5 of 23110 rows