Large language models (LLMs) make it possible to build knowledge graphs from professional literature at scale, but how such graphs fail at that scale is rarely measured. We built \sys{}, a cross-media knowledge graph of swine, aquaculture, tomato, maize and rice production, and analysed its 199,418 entities and 277,053 relations together with the web system that serves it. An LLM extracted typed triples from the professional literature of each sector; 74.9% of the relations carry an evidence record of document, page and excerpt, and a multimodal embedding model links 25,158 entities to images and 14,132 to video clips. We identified five failure modes of construction. First, the sector schem... More >

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 >