# A Method for LLM-Based Construction of a Materials Property Knowledge Graph: A Case Study

https://mdr.nims.go.jp/datasets/ff9d8c80-a789-4295-bf5c-5372ef11be63

## File

- [applsci-15-10511-with-cover.pdf](https://mdr.nims.go.jp/filesets/5b201afa-c36b-4a17-804c-56df35ed975a/download) ([Detail](https://mdr.nims.go.jp/filesets/5b201afa-c36b-4a17-804c-56df35ed975a.md))
- [S1_ list_of_materials_property_names.txt](https://mdr.nims.go.jp/filesets/c9cb3ccb-95f8-4108-b571-1c0e3c3ab00a/download) ([Detail](https://mdr.nims.go.jp/filesets/c9cb3ccb-95f8-4108-b571-1c0e3c3ab00a.md))
- [S2_ list_of_extracted_materials_property_name_ pairs.csv](https://mdr.nims.go.jp/filesets/d3482976-7f3d-465d-a5b2-bd67d7a2bc4f/download) ([Detail](https://mdr.nims.go.jp/filesets/d3482976-7f3d-465d-a5b2-bd67d7a2bc4f.md))

## Id

ff9d8c80-a789-4295-bf5c-5372ef11be63

## Local identifier



## Visibility

open_to_public

## State

published

## Created at

2025-10-31T01:53:32.244529Z

## Updated at

2025-11-04T03:30:07.234405Z

## Published at

2025-11-04T03:27:50.892717Z

## Doi



## First published url

https://doi.org/10.3390/app151910511

## Date published

2025-09-28

## Recorded date published



## Resource type

journal_article

## Manuscript type

vor

## Collection



## Title

- title: 'A Method for LLM-Based Construction of a Materials Property Knowledge Graph:
    A Case Study'
  title_type: original
  lang: en

## Description

- description: " In the field of materials science, experimental data or simulation
    results on material prop ertites are often unevenly distributed. In addition to
    the vast unexplored material space, properties of lesser interest have not been
    measured even for well-studied materials, as exemplified by the discovery of the
    superconductivity of the long-known MgB2. To overcome such challenges, utilizing
    relationships among material properties based on scientific principles can be
    beneficial. We have been constructing a knowledge graph of material property relationships
    using natural language-processing techniques for years. Now, with the surprising
    development of large language models, constructing a knowledge graph has become
    much easier. This article explains what a knowledge graph of material property
    relationships is, presents several types of applications for the knowledge graph,
    and describes how the constructed knowledge graph can be implemented in machine
    learning for predicting material property values. We also demonstrate the construction
    of a knowledge graph of material property relationships and a search system using
    ChatGPT, without any programming, which will be made publicly available."
  description_type: abstract
  lang: und

## Creator

- name: Michiko Yoshitake
  role: author
  orcid: https://orcid.org/0000-0002-0973-5666
  organization: National Institute for Materials Science
  ror: https://ror.org/026v1ze26
- name: Takahiro Nagata
  role: author
  orcid: https://orcid.org/0000-0002-8591-2943
  organization: National Institute for Materials Science
  ror: https://ror.org/026v1ze26

## Contact agent



## Publisher

organization: MDPI AG

## Managing organization



## Keyword

- subject: materials property relationship
  schema: not_defined
- subject: knowledge graph
  schema: not_defined
- subject: " graph search"
  schema: not_defined
- subject: data interpolation
  schema: not_defined
- subject: " generative AI"
  schema: not_defined

## Rights

- identifier: https://creativecommons.org/licenses/by/4.0/

## Other identifier(s)



## Data origin

- data_origin_type: other

## Embargo



## Journal

- title: Applied Sciences
  issn: '20763417'
  volume: '15'
  issue: '19'
  article_number: '10511'

## Conference



## Related item



## Funding

- identifier: JPMJMI21G2
  funder_name: Japan Science and Technology Agency (JST) Mirai Program

## Instrument



## Instrument operator



## Instrument managing organization



## Measurement method



## Specimen



## Chemical composition



## Structure for specimen



## Structural feature for specimen



## Specific property for specimen



## Process for specimen treatment



## Computational method



## Energy level/transition state



## Software



## Custom property



## Fileset

- id: 5b201afa-c36b-4a17-804c-56df35ed975a
  filename: applsci-15-10511-with-cover.pdf
  content_type: application/pdf
  size: 2971497
  md5: cb3733c34df467ac4f036a7b903c3c01
- id: c9cb3ccb-95f8-4108-b571-1c0e3c3ab00a
  filename: S1_ list_of_materials_property_names.txt
  content_type: text/plain
  size: 1878
  md5: 4e559f8eb98f6023ea3820b66c3d653b
- id: d3482976-7f3d-465d-a5b2-bd67d7a2bc4f
  filename: S2_ list_of_extracted_materials_property_name_ pairs.csv
  content_type: text/csv
  size: 16456
  md5: 58a5cc0e33c6617c58fd2c71b1c77614

## Thumbnail

fileset_id: 5b201afa-c36b-4a17-804c-56df35ed975a
filename: applsci-15-10511-with-cover.pdf