This dataset provides plant functional trait information automatically extracted from published taxonomic descriptions for a curated set of UK peatland plant species. The species list comprises 385 angiosperm taxa characteristic of peatland ecosystems in the United Kingdom, assembled to support methodological development and validation of automated trait extraction workflows. Each species was systematically searched across multiple textual sources, including the Biodiversity Heritage Library (BHL; OCR-derived biodiversity literature), eFloras (including Flora of North America, Flora of China, and related online floras), and the Ecological Flora Database (Ecoflora). Where botanical descriptions were identified, natural language processing methods were used to extract structured trait information.

Trait extraction was implemented using the ADEPT pipeline (https://github.com/NaturalHistoryMuseum/ADEPT ), which combines machine-learning classification of botanical descriptions, ontology-driven terminology matching, numeric named-entity recognition, syntactic parsing, and rule-based semantic interpretation to associate traits with plant structures and standardise quantitative measurements.