import spacy

nlp = spacy.load("en_core_web_sm")
doc = nlp("Dr. Alice Chen led the study at Stanford in 2024.")

>>> [(ent.text, ent.label_) for ent in doc.ents]
[('Alice Chen', 'PERSON'), ('Stanford', 'ORG'), ('2024', 'DATE')]
>>> [token.lemma_ for token in doc if not token.is_stop][:5]
['Dr.', 'Alice', 'Chen', 'lead', 'study']
