annotation_task_name: "Named Entity Recognition"
 
data_files:
  - data/sentences.json
 
item_properties:
  id_key: id
  text_key: text
 
# Enable span annotation
annotation_schemes:
  - annotation_type: span
    name: entities
    description: "Highlight and label named entities in the text"
    labels:
      - name: PER
        description: "Person names"
        color: "#FF6B6B"
        keyboard_shortcut: "p"
      - name: ORG
        description: "Organizations"
        color: "#4ECDC4"
        keyboard_shortcut: "o"
      - name: LOC
        description: "Locations"
        color: "#45B7D1"
        keyboard_shortcut: "l"
      - name: DATE
        description: "Dates and times"
        color: "#96CEB4"
        keyboard_shortcut: "d"
      - name: MISC
        description: "Miscellaneous entities"
        color: "#FFEAA7"
        keyboard_shortcut: "m"
    min_spans: 0  # Allow sentences with no entities

{"id": "1", "text": "Apple Inc. announced that CEO Tim Cook will visit Paris next Tuesday."}
{"id": "2", "text": "The United Nations headquarters in New York hosted delegates from Japan."}
{"id": "3", "text": "Dr. Sarah Johnson published her research at Stanford University in March 2024."}

# Add to config.yaml
annotation_guidelines:
  title: "NER Annotation Guidelines"
  content: |
    ## Entity Types
 
    **PER (Person)**: Names of people, including fictional characters
    - Examples: "John Smith", "Dr. Johnson", "Batman"
 
    **ORG (Organization)**: Companies, institutions, agencies
    - Examples: "Apple Inc.", "United Nations", "Stanford University"
 
    **LOC (Location)**: Places, including countries, cities, landmarks
    - Examples: "Paris", "New York", "Mount Everest"
 
    **DATE**: Dates, times, and temporal expressions
    - Examples: "Tuesday", "March 2024", "next week"
 
    **MISC**: Other named entities not fitting above categories
    - Examples: "Nobel Prize", "iPhone", "COVID-19"
 
    ## Annotation Rules
    1. Include titles (Dr., Mr.) with person names
    2. For nested entities, annotate the largest meaningful span
    3. Don't include articles (the, a) in entity spans

potato start config.yaml

{
  "id": "1",
  "text": "Apple Inc. announced that CEO Tim Cook will visit Paris next Tuesday.",
  "annotations": {
    "entities": [
      {"start": 0, "end": 10, "label": "ORG", "text": "Apple Inc."},
      {"start": 30, "end": 38, "label": "PER", "text": "Tim Cook"},
      {"start": 50, "end": 55, "label": "LOC", "text": "Paris"},
      {"start": 61, "end": 73, "label": "DATE", "text": "next Tuesday"}
    ]
  }
}