Docs / Schemas / entity-extraction / 0.5.0

Entity Extraction 0.5.0

Represent named entities, structural slots, or visual concepts extracted from unstructured data. Links raw evidence (text spans or geometric regions) to normalized values and business concepts.

This is an older version of entity-extraction.

The latest version is 0.8.0. Releases before 0.7.0 use the $id https://dorsalhub.com/schemas/open/entity-extraction and are served by DorsalHub.

$id

https://dorsalhub.com/schemas/open/entity-extraction

Latest

https://oatschema.org/entity-extraction

Versions

Source

v0.5.0 on GitHub

Schema

entity-extraction.json Raw

{    "x-license": {        "id": "Apache-2.0",        "notice": "Copyright 2025-2026 Dorsal Hub LTD",        "url": "https://github.com/dorsalhub/open-validation-schemas/blob/main/LICENSE"    },    "$schema": "https://json-schema.org/draft/2020-12/schema",    "$id": "https://dorsalhub.com/schemas/open/entity-extraction",    "title": "Entity Extraction",    "version": "0.5.0",    "description": "Represent named entities, structural slots, or visual concepts extracted from unstructured data. Links raw evidence (text spans or geometric regions) to normalized values and business concepts.",    "type": "object",    "properties": {        "unit": {            "type": "string",            "description": "The unit for all coordinate values if geometric data is present.",            "enum": [                "px",                "pt",                "normalized",                "per_mille"            ]        },        "producer": {            "type": "string",            "description": "The creator (model, tool or author) of this extraction.",            "maxLength": 1024        },        "vocabulary_url": {            "type": "string",            "format": "uri",            "description": "URL to the definition of the entity labels.",            "maxLength": 2048        },        "vocabulary": {            "type": "array",            "description": "Allowed values for the 'label' field.",            "maxItems": 100,            "items": {                "type": "string",                "maxLength": 128            }        },        "score_explanation": {            "type": "string",            "description": "Defines the meaning of the 'score' field.",            "maxLength": 256        },        "entities": {            "type": "array",            "description": "An array of extracted entities.",            "maxItems": 100000,            "items": {                "type": "object",                "properties": {                    "id": {                        "type": "string",                        "description": "A unique identifier for this entity instance (e.g. UUID).",                        "maxLength": 128                    },                    "concept": {                        "type": "string",                        "description": "The business role or slot this entity fills (e.g. 'InvoiceDate', 'Plaintiff'). Optional.",                        "maxLength": 128                    },                    "label": {                        "type": "string",                        "description": "The entity category (e.g. 'PER', 'DATE', 'MONEY').",                        "maxLength": 128                    },                    "text": {                        "type": "string",                        "description": "The raw text span as it appears in the source. Optional for visual entities (e.g. logos, signatures).",                        "maxLength": 4096                    },                    "value": {                        "description": "The machine-readable value (e.g. '2025-11-21', 3500.00, true).",                        "anyOf": [                            {                                "type": "string",                                "maxLength": 4096                            },                            {                                "type": "number"                            },                            {                                "type": "boolean"                            },                            {                                "type": "null"                            }                        ]                    },                    "definition": {                        "type": "string",                        "description": "Definition of the concept.",                        "maxLength": 1024                    },                    "score": {                        "type": "number",                        "description": "The confidence score for this extraction, ranging from 0.0 (uncertain) to 1.0 (certain).",                        "minimum": 0,                        "maximum": 1                    },                    "location": {                        "type": "array",                        "description": "The physical location(s) of the entity.",                        "maxItems": 10,                        "items": {                            "oneOf": [                                {                                    "title": "Block Reference",                                    "type": "object",                                    "properties": {                                        "type": {                                            "const": "block_ref"                                        },                                        "block_id": {                                            "type": "string",                                            "maxLength": 128                                        }                                    },                                    "required": [                                        "type",                                        "block_id"                                    ],                                    "additionalProperties": false                                },                                {                                    "title": "Geometric Location",                                    "type": "object",                                    "properties": {                                        "type": {                                            "const": "block"                                        },                                        "block_type": {                                            "enum": [                                                "box",                                                "polygon"                                            ]                                        },                                        "page_number": {                                            "type": "integer",                                            "minimum": 1                                        },                                        "box": {                                            "type": "object",                                            "properties": {                                                "x": {                                                    "type": "number"                                                },                                                "y": {                                                    "type": "number"                                                },                                                "width": {                                                    "type": "number"                                                },                                                "height": {                                                    "type": "number"                                                }                                            },                                            "required": [                                                "x",                                                "y",                                                "width",                                                "height"                                            ],                                            "additionalProperties": false                                        },                                        "polygon": {                                            "type": "array",                                            "minItems": 3,                                            "maxItems": 100,                                            "items": {                                                "type": "object",                                                "properties": {                                                    "x": {                                                        "type": "number"                                                    },                                                    "y": {                                                        "type": "number"                                                    }                                                },                                                "required": [                                                    "x",                                                    "y"                                                ],                                                "additionalProperties": false                                            }                                        }                                    },                                    "required": [                                        "type",                                        "block_type",                                        "page_number"                                    ],                                    "additionalProperties": false,                                    "allOf": [                                        {                                            "if": {                                                "properties": {                                                    "block_type": {                                                        "const": "box"                                                    }                                                }                                            },                                            "then": {                                                "required": [                                                    "box"                                                ]                                            }                                        },                                        {                                            "if": {                                                "properties": {                                                    "block_type": {                                                        "const": "polygon"                                                    }                                                }                                            },                                            "then": {                                                "required": [                                                    "polygon"                                                ]                                            }                                        }                                    ]                                }                            ]                        }                    },                    "attributes": {                        "type": "object",                        "description": "Arbitrary metadata (e.g. currency, gender). Flat key-value pairs.",                        "maxProperties": 16,                        "additionalProperties": {                            "anyOf": [                                {                                    "type": "string",                                    "maxLength": 1024                                },                                {                                    "type": "number"                                },                                {                                    "type": "boolean"                                },                                {                                    "type": "null"                                }                            ]                        }                    }                },                "required": [                    "label"                ],                "additionalProperties": false            }        },        "attributes": {            "type": "object",            "description": "Arbitrary metadata relevant to this extraction.",            "maxProperties": 16,            "additionalProperties": {                "anyOf": [                    {                        "type": "string",                        "maxLength": 1024                    },                    {                        "type": "number"                    },                    {                        "type": "boolean"                    },                    {                        "type": "null"                    }                ]            }        }    },    "required": [        "entities"    ],    "additionalProperties": false,    "allOf": [        {            "if": {                "properties": {                    "entities": {                        "maxItems": 0                    }                }            },            "then": {                "anyOf": [                    {                        "required": [                            "vocabulary"                        ]                    },                    {                        "required": [                            "vocabulary_url"                        ]                    }                ]            }        },        {            "if": {                "properties": {                    "unit": {                        "const": "normalized"                    }                }            },            "then": {                "properties": {                    "entities": {                        "items": {                            "properties": {                                "location": {                                    "items": {                                        "properties": {                                            "box": {                                                "properties": {                                                    "x": {                                                        "maximum": 1                                                    },                                                    "y": {                                                        "maximum": 1                                                    },                                                    "width": {                                                        "maximum": 1                                                    },                                                    "height": {                                                        "maximum": 1                                                    }                                                }                                            },                                            "polygon": {                                                "items": {                                                    "properties": {                                                        "x": {                                                            "maximum": 1                                                        },                                                        "y": {                                                            "maximum": 1                                                        }                                                    }                                                }                                            }                                        }                                    }                                }                            }                        }                    }                }            }        },        {            "if": {                "properties": {                    "unit": {                        "const": "per_mille"                    }                }            },            "then": {                "properties": {                    "entities": {                        "items": {                            "properties": {                                "location": {                                    "items": {                                        "properties": {                                            "box": {                                                "properties": {                                                    "x": {                                                        "maximum": 1000                                                    },                                                    "y": {                                                        "maximum": 1000                                                    },                                                    "width": {                                                        "maximum": 1000                                                    },                                                    "height": {                                                        "maximum": 1000                                                    }                                                }                                            },                                            "polygon": {                                                "items": {                                                    "properties": {                                                        "x": {                                                            "maximum": 1000                                                        },                                                        "y": {                                                            "maximum": 1000                                                        }                                                    }                                                }                                            }                                        }                                    }                                }                            }                        }                    }                }            }        }    ]}

Fields

unit string

The unit for all coordinate values if geometric data is present.
Allowed values: "px", "pt", "normalized", "per_mille"
producer string

The creator (model, tool or author) of this extraction.
- at most 1024 characters
vocabulary_url string

URL to the definition of the entity labels.
- at most 2048 characters
- format uri
vocabulary array of string

Allowed values for the 'label' field.
- at most 100 items
- each at most 128 characters
score_explanation string

Defines the meaning of the 'score' field.
- at most 256 characters
entities array of object required

An array of extracted entities.
- at most 100000 items
- id string
  
  A unique identifier for this entity instance (e.g. UUID).
  - at most 128 characters
- concept string
  
  The business role or slot this entity fills (e.g. 'InvoiceDate', 'Plaintiff'). Optional.
  - at most 128 characters
- label string required
  
  The entity category (e.g. 'PER', 'DATE', 'MONEY').
  - at most 128 characters
- text string
  
  The raw text span as it appears in the source. Optional for visual entities (e.g. logos, signatures).
  - at most 4096 characters
- value string | number | boolean | null
  
  The machine-readable value (e.g. '2025-11-21', 3500.00, true).
  - string: at most 4096 characters
- definition string
  
  Definition of the concept.
  - at most 1024 characters
- score number
  
  The confidence score for this extraction, ranging from 0.0 (uncertain) to 1.0 (certain).
  - 0 to 1
- location array of object
  
  The physical location(s) of the entity.
  - at most 10 items
  Exactly one of these forms:
  1. Block Reference object
    - type constant "block_ref" required
    - block_id string required
      - at most 128 characters
  2. Geometric Location object
    - type constant "block" required
    - block_type enum required
      
      Allowed values: "box", "polygon"
    - page_number integer required
      - ≥ 1
    - box object
      - x number required
      - y number required
      - width number required
      - height number required
    - polygon array of object
      - 3 to 100 items
      - x number required
      - y number required
    Rules:
    - When block_type is "box", box is required.
      Show the JSON Schema
      { "if": { "properties": { "block_type": { "const": "box" } } }, "then": { "required": [ "box" ] }}
    - When block_type is "polygon", polygon is required.
      Show the JSON Schema
      { "if": { "properties": { "block_type": { "const": "polygon" } } }, "then": { "required": [ "polygon" ] }}
- attributes object
  
  Arbitrary metadata (e.g. currency, gender). Flat key-value pairs.
  - at most 16 properties
  - * string | number | boolean | null
    
    Any other key.
    - string: at most 1024 characters
attributes object

Arbitrary metadata relevant to this extraction.
- at most 16 properties
- * string | number | boolean | null
  
  Any other key.
  - string: at most 1024 characters

Rules:

When entities is empty: at least one of vocabulary, vocabulary_url must be present.

Show the JSON Schema

{  "if": {    "properties": {      "entities": {        "maxItems": 0      }    }  },  "then": {    "anyOf": [      {        "required": [          "vocabulary"        ]      },      {        "required": [          "vocabulary_url"        ]      }    ]  }}

When unit is "normalized", further limits apply.

Show the JSON Schema

{  "if": {    "properties": {      "unit": {        "const": "normalized"      }    }  },  "then": {    "properties": {      "entities": {        "items": {          "properties": {            "location": {              "items": {                "properties": {                  "box": {                    "properties": {                      "x": {                        "maximum": 1                      },                      "y": {                        "maximum": 1                      },                      "width": {                        "maximum": 1                      },                      "height": {                        "maximum": 1                      }                    }                  },                  "polygon": {                    "items": {                      "properties": {                        "x": {                          "maximum": 1                        },                        "y": {                          "maximum": 1                        }                      }                    }                  }                }              }            }          }        }      }    }  }}

When unit is "per_mille", further limits apply.

Show the JSON Schema

{  "if": {    "properties": {      "unit": {        "const": "per_mille"      }    }  },  "then": {    "properties": {      "entities": {        "items": {          "properties": {            "location": {              "items": {                "properties": {                  "box": {                    "properties": {                      "x": {                        "maximum": 1000                      },                      "y": {                        "maximum": 1000                      },                      "width": {                        "maximum": 1000                      },                      "height": {                        "maximum": 1000                      }                    }                  },                  "polygon": {                    "items": {                      "properties": {                        "x": {                          "maximum": 1000                        },                        "y": {                          "maximum": 1000                        }                      }                    }                  }                }              }            }          }        }      }    }  }}