Table 3 Knowledge graph construction performance (on NYT and WebNLG datasets).

From: Knowledge graph construction for intelligent cockpits based on large language models

Methods

NYT

WebNLG

P

R

F1

P

R

F1

CopyRE36

61.0

56.6

58.7

37.7

36.4

37.1

CopyMTL35

75.7

68.7

72.0

58.0

54.9

56.4

PNDec30

80.6

77.3

78.9

-

-

-

CASREL37

89.7

89.5

89.6

93.4

90.1

91.8

CGT29

94.7

84.2

89.1

92.9

75.6

83.4

TPLinker38

91.3

92.5

91.9

91.8

92.0

91.9

SNP39

93.3

91.7

92.5

93.1

93.6

93.4

UIE34

91.9

93.3

92.6

-

-

-

GLM-TripleGen

94.2

93.6

93.9

93.7

93.3

93.5

  1. Best data are indicated in bold.