diff --git a/.gitattributes b/.gitattributes
index 99b4a1023a46293eab15f6f5ecf7dd60c11266f4..67e15b863c6921d05ca2cb7c0af9fc8d13f7a387 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -310,3 +310,4 @@ data/AB/1938/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1939/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1940/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1941/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1942/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
diff --git a/.renku/workflow/abc6e8e7b6554803be67bfb725702458_python.cwl b/.renku/workflow/abc6e8e7b6554803be67bfb725702458_python.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..210ac3d6c8612cb10d37fce16b5d6d8f9ad90f12
--- /dev/null
+++ b/.renku/workflow/abc6e8e7b6554803be67bfb725702458_python.cwl
@@ -0,0 +1,91 @@
+arguments: []
+baseCommand:
+- python
+class: CommandLineTool
+cwlVersion: v1.0
+hints: []
+inputs:
+  input_1:
+    default:
+      class: File
+      path: ../../src/python/run_extract_discussions.py
+    inputBinding:
+      position: 1
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_2:
+    default:
+      class: File
+      path: ../../data/politicians/lastnames/1942_MPs.pickle
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default:
+      class: File
+      path: ../../data/AB/1942/04_correctedxml.tar.gz
+    inputBinding:
+      position: 3
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_4:
+    default:
+      class: File
+      path: ../../data/AB/1942/03_correctedmeta.tar.gz
+    inputBinding:
+      position: 4
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_5:
+    default:
+      class: File
+      path: ../../data/lists/not_names.txt
+    inputBinding:
+      position: 5
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_6:
+    default:
+      class: File
+      path: ../../data/lists/dict_overlaps.pickle
+    inputBinding:
+      position: 6
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_7:
+    default: data/AB/1942/05_annotatedxml.tar.gz
+    inputBinding:
+      position: 7
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: string
+outputs:
+  output_0:
+    outputBinding:
+      glob: $(inputs.input_7)
+    streamable: false
+    type: File
+permanentFailCodes: []
+requirements:
+- class: InlineJavascriptRequirement
+- class: InitialWorkDirRequirement
+  listing:
+  - entry: '$({"listing": [], "class": "Directory"})'
+    entryname: data/AB/1942
+    writable: true
+successCodes: []
+temporaryFailCodes: []
diff --git a/data/AB/1942/05_annotatedxml.tar.gz b/data/AB/1942/05_annotatedxml.tar.gz
new file mode 100644
index 0000000000000000000000000000000000000000..f339f23eacd98253abbc343d22993d6fd5cbb505
--- /dev/null
+++ b/data/AB/1942/05_annotatedxml.tar.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dedcc95cb7285fffef6d4fc18bc243063e44f0919c99c8d70ec948ee10b3cf1f
+size 3809239