The dataset anonymization has not eliminated the re-identification risk, the evaluation of which remains a huge challenge, especially given incomplete statistical information. The re-identification risk of individuals depends on their tuple frequency. The paper proposes the recursive hypergeometric (RH) distribution to accurately calculate the tuple frequency and leverages the binomial distribution to approximate the RH distribution and to efficiently predict the re-identification risk of individuals in both generated and real-world datasets. The experimental results show that our tuple frequency based re-identification risk (TFRR) prediction model has a superior performance (average AUC 0.86~0.98) for all types of datasets. Furthermore, we exploit the value dependence knowledge to rectify the prediction result for some subsets (average AUC 0.95~0.98). Our research reveals the general rule of the tuple frequency distribution and enables individuals and regulators to responsively predict the re-identification risk.