Information　extraction　is　crucial　for　building　and　updating　the　knowledge　base　of　expert　systems.　Large　language　models　face　challenges　with　prompt　sensitivity　and　model　hallucinations　during　information　extraction.　This　study　introduces　the　TIME　(Tourism,　Individuals,　Moments,　Events)　model,　which　organizes　figure-related　information　into　four　main　dimensions:　attributes,　relationships,　events,　and　their　linkage　to　tourism　resources.　Then　present　a　unified　information　extraction　framework　for　figures,　termed　TIME-UIE.　This　framework　integrates　a　unified　task　definition,　a　format　output　constraint,　carefully　selected　demonstrations,　and　knowledge　injection　to　verify　consistency　across　different　inference　chains.　Experimental　results　show　that　TIME-UIE　outperforms　baseline　models　in　deciphering　complex　relationships　between　historical　figures　by　26.2%　and　in　extracting　event　triplets　by　11.1%.　The　study　also　proposes　a　loose　matching　metric　for　model　performance　evaluation,　which　holds　significant　implications　for　the　practical　application　of　the　research　methods.