Implementation:Datajuicer Data juicer ExtractNicknameMapper

Knowledge Sources	Datajuicer_Data_juicer
Domains	Data_Processing, Mapping
Last Updated	2026-02-14 16:00 GMT

Overview

Concrete tool for extracting nickname relationships between characters in text provided by Data-Juicer.

Description

ExtractNicknameMapper is a mapper operator that identifies and extracts nickname relationships from input text using an API-based language model. It sends text to the model with a Chinese system prompt instructing it to identify speaker, addressee, and nickname triples. The structured markdown response is parsed via a verbose regex pattern with cross-validation checks. Results are stored in metadata under the configured nickname key as relationship records containing source entity, target entity, relation description, and relation keywords.

Usage

Use when you need to build character relationship graphs from narrative text, extracting interpersonal nickname and address-form data to understand social dynamics in story-based datasets.

Code Reference

Source Location

• Repository: Datajuicer_Data_juicer
• File: data_juicer/ops/mapper/extract_nickname_mapper.py

Signature

@OPERATORS.register_module("extract_nickname_mapper")
class ExtractNicknameMapper(Mapper):
    def __init__(self,
                 api_model: str = "gpt-4o",
                 *,
                 nickname_key: str = MetaKeys.nickname,
                 api_endpoint: Optional[str] = None,
                 response_path: Optional[str] = None,
                 system_prompt: Optional[str] = None,
                 input_template: Optional[str] = None,
                 output_pattern: Optional[str] = None,
                 try_num: PositiveInt = 3,
                 drop_text: bool = False,
                 model_params: Dict = {},
                 sampling_params: Dict = {},
                 **kwargs):

Import

from data_juicer.ops.mapper.extract_nickname_mapper import ExtractNicknameMapper

I/O Contract

Inputs

Name	Type	Required	Description
api_model	str	No	API model name, defaults to "gpt-4o"
nickname_key	str	No	Key name to store nickname relationships in meta field, defaults to MetaKeys.nickname
api_endpoint	Optional[str]	No	URL endpoint for the API
response_path	Optional[str]	No	Path to extract content from API response
system_prompt	Optional[str]	No	System prompt for the task
input_template	Optional[str]	No	Template for building the model input
output_pattern	Optional[str]	No	Regular expression for parsing model output
try_num	PositiveInt	No	Number of retry attempts on error, defaults to 3
drop_text	bool	No	Whether to drop text from output, defaults to False
model_params	Dict	No	Parameters for initializing the API model
sampling_params	Dict	No	Extra parameters passed to API call

Outputs

Name	Type	Description
samples	Dict	Transformed samples with nickname relationships stored in meta field

Usage Examples

process:
  - extract_nickname_mapper:
      api_model: "gpt-4o"
      try_num: 3
      drop_text: false

Related Pages

• Environment:Datajuicer_Data_juicer_Python_Runtime_Environment