Triple

T14170283
Position Surface form Disambiguated ID Type / Status
Subject Rudi Fehr E351186 entity
Predicate spouse P13 FINISHED
Object Marion Fehr
Marion Fehr is known primarily as the spouse of acclaimed German-American film editor Rudi Fehr.
E1082953 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: Marion Fehr | Statement: [Rudi Fehr, spouse, Marion Fehr]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marion Fehr
Context triple: [Rudi Fehr, spouse, Marion Fehr]
  • A. Toni Krinner
    Toni Krinner was a German ice hockey coach and former player known for his coaching roles in the Deutsche Eishockey Liga.
  • B. Verena Rehm
    Verena Rehm is a German singer and songwriter best known as the female vocalist for the Eurodance project Groove Coverage.
  • C. Franziska Matzelsberger
    Franziska Matzelsberger was the second wife of Alois Hitler and the stepmother of Adolf Hitler.
  • D. Elisabeth Görgl
    Elisabeth Görgl is an Austrian former alpine ski racer and two-time world champion known for her success in speed and technical events on the World Cup circuit.
  • E. Marlies Schild
    Marlies Schild is a retired Austrian alpine ski racer renowned as one of the most successful slalom specialists in World Cup and Olympic history.
  • 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: Marion Fehr
Triple: [Rudi Fehr, spouse, Marion Fehr]
Generated description
Marion Fehr is known primarily as the spouse of acclaimed German-American film editor Rudi Fehr.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Marion Fehr
Target entity description: Marion Fehr is known primarily as the spouse of acclaimed German-American film editor Rudi Fehr.
  • A. Toni Krinner
    Toni Krinner was a German ice hockey coach and former player known for his coaching roles in the Deutsche Eishockey Liga.
  • B. Verena Rehm
    Verena Rehm is a German singer and songwriter best known as the female vocalist for the Eurodance project Groove Coverage.
  • C. Franziska Matzelsberger
    Franziska Matzelsberger was the second wife of Alois Hitler and the stepmother of Adolf Hitler.
  • D. Elisabeth Görgl
    Elisabeth Görgl is an Austrian former alpine ski racer and two-time world champion known for her success in speed and technical events on the World Cup circuit.
  • E. Marlies Schild
    Marlies Schild is a retired Austrian alpine ski racer renowned as one of the most successful slalom specialists in World Cup and Olympic history.
  • 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_69d8278834a08190b0f1784e58d7b99c completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de61b472288190b4a271daa54aa6cd completed April 14, 2026, 3:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcf7f779248190921c85f99f587296 completed May 7, 2026, 8:37 p.m.
NEDg Description generation batch_69fcf8bb58ac81908e66156a805edda8 completed May 7, 2026, 8:40 p.m.
NED2 Entity disambiguation (via description) batch_69fcf93b528c81908c0ee11908d25574 completed May 7, 2026, 8:42 p.m.
Created at: April 10, 2026, 1:01 a.m.