Exploring a Large Language Model for Transforming Taxonomic Data into OWL: Lessons Learned and Implications for Ontology Development

2025-03-01

Data Intelligence

AI Summary

Manual maintenance of taxonomic species names in agricultural ontologies is costly and struggles to keep pace with dynamic taxonomic revisions. Method: This paper pioneers a systematic investigation into the feasibility of directly generating OWL ontologies using large language models (LLMs), proposing a dual-path prompting strategy: (1) an interactive browser extension for ontology construction, and (2) an LLM-driven Python script for batch generation. Leveraging ChatGPT-4 and the GBIF Backbone API, we automatically construct the :Organism module of the Agricultural Product Type Ontology (APTO), producing standards-compliant OWL 2 files. Contribution/Results: The second path enables scalable processing of over one thousand species per batch, achieving >85% accuracy. This work demonstrates the practical utility of LLMs for managing evolving taxonomic data and establishes a novel, scalable, low-barrier automation paradigm for ontology engineering.

Technology Category

• Knowledge Representation and Reasoning: Ontologies
• Natural Language Processing: Generation
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Managing scientific names in ontologies that represent species taxonomies is challenging due to the ever-evolving nature of these taxonomies. Manually maintaining these names becomes increasingly difficult when dealing with thousands of scientific names. To address this issue, this paper investigates the use of ChatGPT-4 to automate the development of the :Organism module in the Agricultural Product Types Ontology (APTO) for species classification. Our methodology involved leveraging ChatGPT-4 to extract data from the GBIF Backbone API and generate OWL files for further integration in APTO. Two alternative approaches were explored: (1) issuing a series of prompts for ChatGPT-4 to execute tasks via the BrowserOP plugin and (2) directing ChatGPT-4 to design a Python algorithm to perform analogous tasks. Both approaches rely on a prompting method where we provide instructions, context, input data, and an output indicator. The first approach showed scalability limitations, while the second approach used the Python algorithm to overcome these challenges, but it struggled with typographical errors in data handling. This study highlights the potential of Large language models like ChatGPT-4 to streamline the management of species names in ontologies. Despite certain limitations, these tools offer promising advancements in automating taxonomy-related tasks and improving the efficiency of ontology development.

Problem

• Automating species name management in ontologies using ChatGPT-4
• Transforming taxonomic data into OWL for ontology development
• Addressing scalability and data errors in automated taxonomy tasks

Innovation

• Using ChatGPT-4 to automate OWL file generation
• Leveraging Python algorithms for scalable data processing
• Integrating GBIF Backbone API for taxonomic data extraction