Tomato disease knowledge is scattered across agronomic texts and leaf images from heterogeneous sources, and static knowledge graphs that write extraction outputs directly to a database cannot separate model candidates from currently valid facts. We construct a multimodal knowledge graph for tomato diseases together with an evidence-gated dynamic update workflow. On the text side, a Chinese-RoBERTa-wwm-ext encoder with GlobalPointer identifies entity spans, and a directed relation pointer network extracts relations. On the image side, Chinese-CLIP fine-tuned with supervised contrastive learning aligns disease images with disease-text prototypes. On the graph side, stable entity and fact iden... More >