RELRaE: LLM-Based Relationship Extraction, Labelling, Refinement, and Evaluation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hannah, George, de Berardinis, Jacopo, Payne, Terry R., Tamma, Valentina, Mitchell, Andrew, Piercy, Ellen, Johnson, Ewan, Ng, Andrew, Rostron, Harry, Konev, Boris
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909675911380992
author Hannah, George
de Berardinis, Jacopo
Payne, Terry R.
Tamma, Valentina
Mitchell, Andrew
Piercy, Ellen
Johnson, Ewan
Ng, Andrew
Rostron, Harry
Konev, Boris
author_facet Hannah, George
de Berardinis, Jacopo
Payne, Terry R.
Tamma, Valentina
Mitchell, Andrew
Piercy, Ellen
Johnson, Ewan
Ng, Andrew
Rostron, Harry
Konev, Boris
contents A large volume of XML data is produced in experiments carried out by robots in laboratories. In order to support the interoperability of data between labs, there is a motivation to translate the XML data into a knowledge graph. A key stage of this process is the enrichment of the XML schema to lay the foundation of an ontology schema. To achieve this, we present the RELRaE framework, a framework that employs large language models in different stages to extract and accurately label the relationships implicitly present in the XML schema. We investigate the capability of LLMs to accurately generate these labels and then evaluate them. Our work demonstrates that LLMs can be effectively used to support the generation of relationship labels in the context of lab automation, and that they can play a valuable role within semi-automatic ontology generation frameworks more generally.
format Preprint
id arxiv_https___arxiv_org_abs_2507_03829
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RELRaE: LLM-Based Relationship Extraction, Labelling, Refinement, and Evaluation
Hannah, George
de Berardinis, Jacopo
Payne, Terry R.
Tamma, Valentina
Mitchell, Andrew
Piercy, Ellen
Johnson, Ewan
Ng, Andrew
Rostron, Harry
Konev, Boris
Artificial Intelligence
I.2.4; I.2.1
A large volume of XML data is produced in experiments carried out by robots in laboratories. In order to support the interoperability of data between labs, there is a motivation to translate the XML data into a knowledge graph. A key stage of this process is the enrichment of the XML schema to lay the foundation of an ontology schema. To achieve this, we present the RELRaE framework, a framework that employs large language models in different stages to extract and accurately label the relationships implicitly present in the XML schema. We investigate the capability of LLMs to accurately generate these labels and then evaluate them. Our work demonstrates that LLMs can be effectively used to support the generation of relationship labels in the context of lab automation, and that they can play a valuable role within semi-automatic ontology generation frameworks more generally.
title RELRaE: LLM-Based Relationship Extraction, Labelling, Refinement, and Evaluation
topic Artificial Intelligence
I.2.4; I.2.1
url https://arxiv.org/abs/2507.03829