A Method for LLM-Based Construction of a Materials Property Knowledge Graph: A Case Study
Source abstract
Abstract
In the field of materials science, experimental data or simulation results on material properties 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.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Machine Learning in Materials Science · Manufacturing Process and Optimization
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
National Institute for Material Science, Tsukuba 305-0047, Japan
MatQ-lab, Chiba 271-0092, Japan
Funding
Japan Science and Technology Agency (JST) Mirai Program
References (44)
Show source-provided references
1. Opportunities and limitations of the ChatGPT Advanced Data Analysis plugin for hydrological analyses10.1002/hyp.15015 ↗
2. Prompt engineering of GPT-4 for chemical research: What can/cannot be done?
3. Lu, C., Lu, C., Lange, R.T., Foerster, J., Clune, J., and Ha, D. (2024). The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery. arXiv.
4. Shir, O.M. (ChemRxiv, 2024). Towards AI Research Agents in the Chemical Sciences, ChemRxiv.10.26434/chemrxiv-2024-lf2xx ↗
5. (2025, July 25). WikiPedia, Knowledge Graph. Available online: https://en.wikipedia.org/wiki/Knowledge_graph.
6. Dilmegani, C. (2025, July 25). In-Depth Guide to Knowledge Graph: Use Cases 2025. Available online: https://research.aimultiple.com/knowledge-graph/.
7. Tesfaye, L. (2025, July 25). Top Graph Use Cases and Enterprise Applications (with Real World Examples). Available online: https://enterprise-knowledge.com/top-graph-use-cases-and-enterprise-applications-with-real-world-examples/.
8. (2025, July 25). Shakudo, Top 9 Knowledge Graphs Use Cases. Available online: https://cdn.prod.website-files.com/625447c67b621ab49bb7e3e5/67a3c0688035b75e2f4ca37a_pdf-knowledge%20graph%20use%20cases.pdf.
9. Sajid, H. (2025, July 25). 20 Real-World Industrial Applications of Knowledge Graphs. Available online: https://www.wisecube.ai/blog/20-real-world-industrial-applications-of-knowledge-graphs/.
10. Mishram, C. (2025, July 25). Popular and Unique Knowledge Graph Use Cases for Data Analytics. Available online: https://scikiq.com/blog/popular-and-unique-knowledge-graph-use-cases-for-data-analytics/.
11. propnet: A Knowledge Graph for Materials Science10.1016/j.matt.2019.11.013 ↗
12. Zhao, X., Greenberg, J., McClellan, S., Hu, Y.-J., Lopez, S., Saikin, S.K., Hu, X., and An, Y. (2021, January 15–18). Knowledge Graph-Empowered Materials Discovery. Proceedings of the 2021 IEEE International Conference on Big Data (Big Data), Orlando, FL, USA.10.1109/BigData52589.2021.9671503 ↗
13. Venugopal, V., Pai, S., and Olivetti, E. (December, January 28). The Largest Knowledge Graph in Materials Science—Entities, Relations, and Link Prediction through Graph Representation Learning. Proceedings of the 36th Conference on Neural Information Processing Systems (NeurIPS 2022), New Orleans, LA, USA. Available online: https://openreview.net/forum?id=xyJ_0-WCIZN.
14. Ye, Y., Ren, J., Wang, S., Wan, Y., Razzak, I., Hoex, B., Wang, H., Xie, T., and Zhang, W. (2024, January 9–15). Construction and Application of Materials Knowledge Graph in Multidisciplinary Materials Science via Large Language Model. Proceedings of the 38th Conference on Neural Information Processing Systems (NeurIPS 2024), Vancouver, BC, Canada.
15. MatKG: An autonomously generated knowledge graph in Material Science10.1038/s41597-024-03039-z ↗
16. Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W., and Rocktäschel, T. (2021). Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. arXiv.
17. IBM Newsletter (2025, July 25). What Is Retrieval-Augmented Generation?. Available online: https://research.ibm.com/blog/retrieval-augmented-generation-RAG?ref=blog.zatrok.com.
18. Liang, L., Sun, M., Gui, Z., Zhu, Z., Jiang, Z., Zhong, L., Qu, Y., Zhao, P., Bo, Z., and Yang, J. (2024). KAG: Boosting LLMs in Professional Domains via Knowledge Augmented Generation. arXiv.10.1145/3701716.3715240 ↗
19. Procko, T.T., and Ochoa, O. (October, January 30). Graph Retrieval-Augmented Generation for Large Language Models: A Survey. Proceedings of the 2024 Conference on AI, Science, Engineering, and Technology (AIxSET), Laguna Hills, CA, USA.10.1109/AIxSET62544.2024.00030 ↗
20. Yoshitake, M. (2016, January 29–22). Searching System on Network of Various Materials Properties for Materials Curation. Proceedings of the 63rd JSAP Spring Meeting, Tokyo, Japan. Presentation #21p-S322-2.
21. Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K. (2018). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arXiv.
22. NIMS patents: See patents section.
23. Yoshitake, M., and Kawano, H. (2023). Material Curation® Support System: Prototype. Jxiv, (In Japanese).
24. Yoshitake, M. (2023). Materials Curation® Support System: Case studies. Jxiv.
25. WikiPedia (2025, July 25). List of Thermal Conductivities. Available online: https://en.wikipedia.org/wiki/List_of_thermal_conductivities.
26. WikiPedia (2025, July 25). 1370 Aluminium Alloy. Available online: https://en.wikipedia.org/wiki/1370_aluminium_alloy.
27. Thermtest (2025, July 25). Materials Thermal Properties Database. Available online: https://thermtest.com/thermal-resources/materials-database.
28. Engineering ToolBox (2025, July 25). Thermal Conductivity of Metals and Alloys: Data Table & Reference Guide. Available online: https://www.engineeringtoolbox.com/thermal-conductivity-metals-d_858.html.
29. WikiPedia (2025, July 25). Titanium. Available online: https://en.wikipedia.org/wiki/Titanium.
30. WikiPedia (2025, July 25). Tungsten. Available online: https://en.wikipedia.org/wiki/Tungsten.
31. WikiPedia (2025, July 25). Platinum. Available online: https://en.wikipedia.org/wiki/Platinum.
32. Generic trend of work functions in transition-metal carbides and nitrides10.1116/1.4901014 ↗
33. Yoshitake, M. (2021). Tool for Designing Breakthrough Discovery in Materials Science. Materials, 14.10.3390/ma14226946 ↗
34. PoLyInfo (2025, July 25). National Institute for Materials Science (NIMS), Available online: https://polymer.nims.go.jp/.
35. Callister, W.D., and Rethwisch, D.G. (2010). Materials Science and Engineering—An Introduction, John Wiley & Sons. [8th ed.].
36. Utilizing Knowledge on Scientific Principles on Material Properties for Materials R&D10.1384/jsa.26.134 ↗
37. Networked Knowledge and Complex Networks: An Engineering View10.1109/JAS.2022.105737 ↗
38. Gao, Y., Xiong, Y., Gao, X., Jia, K., Pan, J., Bi, Y., Dai, Y., Sun, J., and Wang, H. (2023). Retrieval-Augmented Generation for Large Language Models: A Survey. arXiv.
39. Zhang, Q., Chen, S., Bei, Y., Yuan, Z., Zhou, H., Hong, Z., Dong, J., Chen, H., Chang, Y., and Huang, X. (2025). A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models. arXiv.
40. Oxide Superconductors10.1111/j.1151-2916.2000.tb01142.x ↗
41. National Institute for Materials Science, Japan (2022). Retrieval System and Retrieval Method. (7186436), Patent JP: No., (In Japanese).
42. Ye, Y., Ren, J., Wang, S., Wan, Y., Razzak, I., Hoex, B., Wang, H., Xie, T., and Zhang, W. (2024). Construction and Application of Materials Knowledge Graph in Multidisciplinary Materials Science via Large Language Model. arXiv.
43. Revisiting Electrocatalyst Design by a Knowledge Graph of Cu-Based Catalysts for CO2 Reduction10.1021/acscatal.3c00759 ↗
44. Generating knowledge graphs through text mining of catalysis research related literature10.1039/D4CY00369A ↗