Revert split-author entries in gold and adapt global instructions

docs/tei-element-descriptions.md

@@ -34,15 +34,17 @@ act at all.
 
 ---
 
-### 2. State multiplicity explicitly
+### 2. State multiplicity and grouping rules explicitly
 
-Without an explicit instruction, models default to merging all instances into
-one span.
+Without explicit instructions, models may make wrong choices about how many
+spans to emit.
 
 **Bad:** "Name(s) of the author(s) of the cited work."
 
-**Good:** "Emit a **separate** `author` span for each distinct author — never
-merge multiple authors into a single span."
+**Good:** "All name parts (`surname`, `forename`, `orgName`) for one or more
+contiguous authors may be placed inside a single `author` span. Emit a separate
+`author` span only when authors are separated by non-name text (e.g. a title or
+date between them)."
 
 This applies to any element that can appear more than once: `author`, `editor`,
 `biblScope` (volume vs. issue), `date` (publication year vs. original year), etc.

scripts/evaluate_llm.py

@@ -145,8 +145,9 @@ def _build_schema():
             "'author' or 'editor' span.",
             "When an organisation acts as author or editor, emit BOTH an 'orgName' span AND an "
             "enclosing 'author' (or 'editor') span covering the same text.",
-            "Emit a separate 'author' span for each distinct author — never merge multiple "
-            "authors into a single span.",
+            "All name parts (surname, forename, orgName) for one or more contiguous authors "
+            "may be placed inside a single 'author' (or 'editor') span. Emit separate spans "
+            "only when authors are separated by non-name text (e.g. a title or date).",
             "In a bibliography, a dash or underscore may stand for a repeated author or editor "
             "name — tag it as 'author' or 'editor' accordingly.",
         ],

tests/fixtures/blbl-examples.tei.xml

@@ -22,11 +22,11 @@
     <bibl><author><surname>Bugnon</surname> (<forename>A.-L.</forename>)</author>, <title level="a">Le mobilier céramique</title>, in <editor><surname>Méloche</surname></editor> <date>2012</date>, p. <biblScope unit="page">182-196</biblScope>.</bibl>
     <bibl><author><orgName>Commission Inter-IREM Collège</orgName></author> &amp; <author><orgName>Commission Inter-IREM Statistiques et Probabilités</orgName></author>, (<date>2012</date>). <title level="a">Probabilités au collège : ne pas laisser l’enseignement des probabilités au hasard…</title>. Dans <title level="j">Brochure APMEP</title> n°<biblScope unit="volume">198</biblScope>.</bibl>
     <bibl><author><surname>BARIL</surname>, <forename>Jean</forename></author> (<date>2013</date>). <title level="a">Droit d’accès à l’information environnementale</title>. <publisher>Éditions Yvon Blais</publisher>, <pubPlace>Cowansville, Québec</pubPlace>, <biblScope unit="page">561 p</biblScope>.</bibl>
-    <bibl><author><surname>Russell</surname>, <forename>D.A.</forename></author> and <author><forename>Michael</forename> <surname>Winterbottom</surname></author> <date>1989</date> [<date>1972</date>]. <title level="m">Classical Literary Criticism. Oxford World Classics</title>. <pubPlace>Oxford</pubPlace>: <publisher>Oxford UP</publisher>.</bibl>
+    <bibl><author><surname>Russell</surname>, <forename>D.A.</forename> and <forename>Michael</forename> <surname>Winterbottom</surname></author> <date>1989</date> [<date>1972</date>]. <title level="m">Classical Literary Criticism. Oxford World Classics</title>. <pubPlace>Oxford</pubPlace>: <publisher>Oxford UP</publisher>.</bibl>
     <bibl><author><surname>Doyle</surname> <forename>JJ.</forename></author> <date>1998</date>. <title level="a">Phylogenetic perspectives on nodulation: evolving views of plants and symbiotic bacteria</title>. &lt;italic&gt;<title level="j">Trends in Plant Science</title>&lt;/italic&gt; <biblScope unit="volume">3</biblScope>: <biblScope unit="page">473-478</biblScope>.</bibl> 
     <bibl><author><surname>Doyle</surname> <forename>JJ</forename></author>. <date>2011</date>. <title level="a">Phylogenetic perspectives on the origins of nodulation</title>. &lt;italic&gt;<title level="j">Molecular Plant-Microbe Interaction</title>&lt;/italic&gt; <biblScope unit="volume">24</biblScope>: <biblScope unit="page">1289-1295</biblScope>.</bibl>
-    <bibl><label>17.</label><author><surname>Creed</surname> <forename>PA</forename></author>, <author><surname>Hicks</surname> <forename>RE</forename></author>, <author><surname>Machin</surname> <forename>MA</forename></author>. <title level="a">Behavioural plasticity and mental health outcomes for long-term unemployed attending occupational training programmes</title>. <title level="j">J Occup Org Psychol</title>. <date>1998</date>;<biblScope unit="volume">71</biblScope>: <biblScope unit="page">171-91</biblScope>.</bibl>
-    <bibl><label>25.</label> <author><surname>Spickett-Jones</surname>, <forename>J. G.</forename></author> &amp; <author><forename>T.-Y.</forename> <surname>Eng</surname></author> (<date>2006</date>). “<title level="a">SMEs and the Strategic Context for Communication</title>”’, <title level="j">Journal of Marketing Communications</title>, Vol. <biblScope unit="volume">12</biblScope>(<biblScope unit="issue">3</biblScope>), <biblScope unit="page">225 - 243</biblScope>.</bibl>
+    <bibl><label>17.</label><author><surname>Creed</surname> <forename>PA</forename>, <surname>Hicks</surname> <forename>RE</forename>, <surname>Machin</surname> <forename>MA</forename></author>. <title level="a">Behavioural plasticity and mental health outcomes for long-term unemployed attending occupational training programmes</title>. <title level="j">J Occup Org Psychol</title>. <date>1998</date>;<biblScope unit="volume">71</biblScope>: <biblScope unit="page">171-91</biblScope>.</bibl>
+    <bibl><label>25.</label> <author><surname>Spickett-Jones</surname>, <forename>J. G.</forename> &amp; <forename>T.-Y.</forename> <surname>Eng</surname></author> (<date>2006</date>). “<title level="a">SMEs and the Strategic Context for Communication</title>”’, <title level="j">Journal of Marketing Communications</title>, Vol. <biblScope unit="volume">12</biblScope>(<biblScope unit="issue">3</biblScope>), <biblScope unit="page">225 - 243</biblScope>.</bibl>
     <bibl><author><surname>Lillié</surname>, <forename>F.</forename></author>, <title level="m">Analyse tectonique de Gisement Claude</title> (<pubPlace>Cluff Lake, Saskatchewan</pubPlace>). <note type="report">Amok Internal Report</note>. <date>1982</date>.</bibl>
     <bibl><author><surname>Netto</surname>, <forename>S.</forename></author> (<date>2010</date>). <title level="a">Représentation de l&apos;informatique à l&apos;école chez de futurs enseignants et des enseignants en poste</title>. <title level="j">Les dossiers des sciences de l&apos;Education</title>(<biblScope unit="volume">23</biblScope>), pp. <biblScope unit="page">61-76</biblScope>.</bibl>
     <bibl><author><surname>Jakobson</surname>, <forename>Roman</forename></author> <date>1960</date>. "<title level="a">Closing Statement: Linguistics and Poetics</title>.” In <editor><forename>Thomas A.</forename> <surname>Sebeok</surname></editor>, ed. <title level="m">Style in Language</title>. <pubPlace>Cambridge, Mass</pubPlace>: <publisher>The MIT Press</publisher>. <biblScope unit="page">350-77</biblScope></bibl>