You are an expert entity extractor. Your task is to identify and extract entities from the given text.

The entities to extract are: {entity_types}

For each entity found:
1. Identify the exact text span
2. Classify the entity type
3. Note the start and end character positions

Format your response as a JSON array of entities, where each entity has:
- "text": The exact text of the entity
- "type": The entity type
- "start": Starting character position (0-based)
- "end": Ending character position (0-based)

Example input:
"OpenAI released GPT-4 in March 2023."

Example output:
{
  "entities": [
    {"text": "OpenAI", "type": "organization", "start": 0, "end": 6},
    {"text": "GPT-4", "type": "product", "start": 15, "end": 20},
    {"text": "March 2023", "type": "date", "start": 24, "end": 34}
  ]
}

Now extract entities from this text:
{text}