diff --git a/.gitattributes b/.gitattributes
index 5e1530c94e57f32efeb523746edcd85285de046f..cb38f32f3fb3afb3d91cc32e36c847e1ceb093c5 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -424,3 +424,4 @@ data/AB/1947/06_collectedinformation.pickle filter=lfs diff=lfs merge=lfs -text
 data/AB/1948/06_collectedinformation.pickle filter=lfs diff=lfs merge=lfs -text
 data/AB/1949/06_collectedinformation.pickle filter=lfs diff=lfs merge=lfs -text
 data/AB/1950/06_collectedinformation.pickle filter=lfs diff=lfs merge=lfs -text
+data/AB/1951/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
diff --git a/.renku/workflow/f196285329a2430690b9e4b4dd70ee63_python.cwl b/.renku/workflow/f196285329a2430690b9e4b4dd70ee63_python.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..cb91963356cb5dcf5c33220f867fcc75fe9347bf
--- /dev/null
+++ b/.renku/workflow/f196285329a2430690b9e4b4dd70ee63_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/yearly_pickles/1951_MPs.pickle
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default:
+      class: File
+      path: ../../data/AB/1951/04_correctedxml.tar.gz
+    inputBinding:
+      position: 3
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_4:
+    default:
+      class: File
+      path: ../../data/AB/1951/03_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/1951/05_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/1951
+    writable: true
+successCodes: []
+temporaryFailCodes: []
diff --git a/data/AB/1951/05_annotatedxml.tar.gz b/data/AB/1951/05_annotatedxml.tar.gz
new file mode 100644
index 0000000000000000000000000000000000000000..a823e39ff20f44ee32aa653eb45edae91e43505c
--- /dev/null
+++ b/data/AB/1951/05_annotatedxml.tar.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33c3c53102fe8fafd5a784de2a927e1ed99be24f1eb208a7cda8c60672bb48a9
+size 9212404