correct = [['*','*'],['*','PER','*','GPE','ORG'],['GPE','*','*','*','ORG']]
predicted = [['PER','*'],['*','ORG','*','GPE','ORG'],['PER','*','*','*','MISC']]

correct = [['*','*'],['*','PER','*','GPE','ORG'],['GPE','*','*','*','ORG']]
predicted = [['PER','*'],['*','ORG','*','GPE','ORG'],['PER','*','*','*','MISC']]
target_names = ['PER','ORG','MISC','LOC','GPE', '*']  # keep '*' last

correct_flat = [item for sublist in correct for item in sublist]
predicted_flat = [item for sublist in predicted for item in sublist]

from sklearn.metrics import classification_report
print(classification_report(correct_flat, predicted_flat, target_names=target_names))

precision    recall  f1-score   support

        PER       1.00      0.86      0.92         7
        ORG       1.00      0.50      0.67         2
       MISC       0.00      0.00      0.00         0
        LOC       0.50      0.50      0.50         2
        GPE       0.00      0.00      0.00         1

avg / total       0.83      0.67      0.73        12

UndefinedMetricWarning: Recall and F-score are ill-defined and being set to 0.0 in labels with no true samples.