diff --git a/.gitattributes b/.gitattributes
index b4f5612d0b17d45dedd11bec43b08e8d83a32fcb..ac10aa05d2498e62eb894d01aca5f87af3bd3a5a 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -270,3 +270,4 @@ data/AB/1899/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1900/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1991/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1901/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1902/05_annotatedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
diff --git a/.renku/workflow/817b71eed0e5460e84625b9a742681ec_python.cwl b/.renku/workflow/817b71eed0e5460e84625b9a742681ec_python.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..0f4cad96f746e07e8806d6829f8295eb1c6c82d6
--- /dev/null
+++ b/.renku/workflow/817b71eed0e5460e84625b9a742681ec_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/1902_MPs.pickle
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default:
+      class: File
+      path: ../../data/AB/1902/04_correctedxml.tar.gz
+    inputBinding:
+      position: 3
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_4:
+    default:
+      class: File
+      path: ../../data/AB/1902/03_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/1902/05_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/1902
+    writable: true
+successCodes: []
+temporaryFailCodes: []
diff --git a/data/AB/1902/05_annotatedxml.tar.gz b/data/AB/1902/05_annotatedxml.tar.gz
new file mode 100644
index 0000000000000000000000000000000000000000..ef42d4a8fc7495afdf38d8d0c9cca3c43479007b
--- /dev/null
+++ b/data/AB/1902/05_annotatedxml.tar.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5ce4302b5cbe94e485e2588fd2f5c16c4c7bf1882236800d1563566af13b7c0
+size 3921369