B³/CEAF (B-Cubed / Constrained Entity-Alignment F-Measure) is a key evaluation metric for the coreference resolution task in the field of natural language processing. B³ and CEAF calculate F1 scores based on entity mention partitioning and core entity alignment, respectively, providing complementary measures of coreference resolution quality. This metric is typically reported as a percentage or a score between 0 and 1. It is widely used in relevant benchmarks and papers, effectively reflecting model performance along this dimension. Higher values indicate better performance.