K
K-9
Text
LLM-Extracted Database of Thermoelectric Materials
An open-access database of 7,123 thermoelectric compounds - chemical composition, structural detail, Seebeck coefficient, electrical and thermal conductivity, power factor, and figure of merit (ZT) - constructed by applying the GPTArticleExtractor large-language-model workflow to automatically extract and curate property data from published scientific literature (Elsevier journals). It replaces error-prone manual data collection with structured, machine-assisted curation to enable data-driven thermoelectric materials analysis and discovery.