Triple

T9283924
Position Surface form Disambiguated ID Type / Status
Subject From the Life of the Marionettes E223137 entity
Predicate castMember P1668 FINISHED
Object Lola Müthel
Lola Müthel was a German actress known for her work in film, television, and theater during the mid-20th century.
E789578 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Lola Müthel | Statement: [From the Life of the Marionettes, castMember, Lola Müthel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lola Müthel
Context triple: [From the Life of the Marionettes, castMember, Lola Müthel]
  • A. Kaja Fehr
    Kaja Fehr is an editor known for her work on the film "One Christmas."
  • B. Johanna Pfaelzer
    Johanna Pfaelzer is an American theatre producer and arts leader known for her work developing new plays and serving in top artistic leadership roles at major regional theatres.
  • C. Mandy Wötzel
    Mandy Wötzel is a German former pair skater best known for winning the 1997 World Championship and the 1994 Olympic silver medal with partner Ingo Steuer.
  • D. Gina-Maria Schumacher
    Gina-Maria Schumacher is a German equestrian athlete and the daughter of seven-time Formula One world champion Michael Schumacher.
  • E. Franziska Matzelsberger
    Franziska Matzelsberger was the second wife of Alois Hitler and the stepmother of Adolf Hitler.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Lola Müthel
Triple: [From the Life of the Marionettes, castMember, Lola Müthel]
Generated description
Lola Müthel was a German actress known for her work in film, television, and theater during the mid-20th century.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Lola Müthel
Target entity description: Lola Müthel was a German actress known for her work in film, television, and theater during the mid-20th century.
  • A. Kaja Fehr
    Kaja Fehr is an editor known for her work on the film "One Christmas."
  • B. Johanna Pfaelzer
    Johanna Pfaelzer is an American theatre producer and arts leader known for her work developing new plays and serving in top artistic leadership roles at major regional theatres.
  • C. Mandy Wötzel
    Mandy Wötzel is a German former pair skater best known for winning the 1997 World Championship and the 1994 Olympic silver medal with partner Ingo Steuer.
  • D. Gina-Maria Schumacher
    Gina-Maria Schumacher is a German equestrian athlete and the daughter of seven-time Formula One world champion Michael Schumacher.
  • E. Franziska Matzelsberger
    Franziska Matzelsberger was the second wife of Alois Hitler and the stepmother of Adolf Hitler.
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69ca842123588190b3f2e1a69037d141 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd081e72988190917f425e64631837 completed April 1, 2026, 11:57 a.m.
NED1 Entity disambiguation (via context triple) batch_69d0b2134d408190b21c7dc642549fe4 completed April 4, 2026, 6:39 a.m.
NEDg Description generation batch_69d0b301659481909c1865884421fcde completed April 4, 2026, 6:43 a.m.
NED2 Entity disambiguation (via description) batch_69d0b38ae1ec8190b36019d3a642290d completed April 4, 2026, 6:45 a.m.
Created at: March 30, 2026, 7:34 p.m.