```json { "table_name": "ae", "primary_key": "USUBJID,AESEQ", "candidates": [ { "rank": 0, "partition_key": "USUBJID", "partition_key_label": "E", "partition_key_reasoning": "USUBJID is the entity column (subject/patient ID) with RPUV=5.29 (225 unique subjects, ~5 adverse events per subject on average). Top 3 coverage is 4.87%, indicating good distribution. This is the natural entity perspective for clinical adverse event tracking — each subject's timeline of adverse events.", "clustering_key": "AEDTC", "clustering_key_label": "S", "clustering_key_reasoning": "AEDTC is the adverse event date/time with monotonicity=0.489 and 453 unique values. This is the temporal ordering axis within each subject's adverse event history. AESEQ is a sequence number but AEDTC provides the actual chronological ordering.", "world_line": "USUBJID", "session_column": null, "confidence": "HIGH", "notes": "This is a clinical trial adverse event (AE) table following CDISC SDTM standards. Each row represents one adverse event occurrence for a subject. The natural partition is by USUBJID (subject ID) to group all adverse events per patient, ordered by AEDTC (event date). The composite primary key (USUBJID, AESEQ) uniquely identifies each adverse event record. AESEQ provides within-subject event numbering but AEDTC gives the actual temporal sequence." } ] } ```