In a long-term evolution experiment with Escherichia coli, bacteria in one of twelve populations evolved the ability to consume citrate, a previously unexploited resource in a glucose-limited medium. This innovation led to the frequency-dependent coexistence of citrate-consuming (Cit+) and non-consuming (Cit-) ecotypes, with Cit-bacteria persisting on the exogenously supplied glucose as well as other carbon molecules released by the Cit+ bacteria. After more than 10,000 generations of coexistence, however, the Cit-lineage went extinct; cells with the Cit-phenotype dropped to levels below detection, and the Cit-clade could not be detected by molecular assays based on its unique genotype. We hypothesized that this extinction was a deterministic outcome of evolutionary change within the population, specifically the appearance of a more-fit Cit+ ecotype that competitively excluded the Cit-ecotype. We tested this hypothesis by re-evolving the population from a frozen population sample taken within 500 generations of the extinction and from another sample taken several thousand generations earlier, in each case for 500 generations and with 20-fold replication. To our surprise, the Cit-type did not go extinct in any of these replays, and Cit-cells also persisted in a single replicate that was propagated for 2,500 generations. Even more unexpectedly, we showed that the Cit-ecotype could reinvade the Cit+ population after its extinction. Taken together, these results indicate that the extinction of the Cit-ecotype was not a deterministic outcome driven by competitive exclusion by the Cit+ ecotype. The extinction also cannot be explained by demographic stochasticity alone, as the population size of the Cit-ecotype should have been many thousands of cells even during the daily transfer events. Instead, we infer that the extinction must have been caused by a rare chance event in which some aspect of the experimental conditions was inadvertently perturbed.