Multi-modal Earth Observation pretraining dataset in TACO format. Part A: 250k monotemporal tiles, Part B: ~12.5k locations × 12 monthly timesteps, Part C: ~16.6k locations × 6 five-daily timesteps. Sensors: Sentinel-2 L1C, Landsat 8/9, Copernicus DEM, ESA WorldCover. Locations selected via AEF hierarchical clustering over the MajorTOM 10km grid. Funded by the ELLIOT project.