Triple

T18690868
Position Surface form Disambiguated ID Type / Status
Subject Klaus Kinski E456994 entity
Predicate spouse P13 FINISHED
Object Gislinde Kühlbeck
Gislinde Kühlbeck is known as the spouse of the late German actor Klaus Kinski.
 E1342282 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: Gislinde Kühlbeck | Statement: [Klaus Kinski, spouse, Gislinde Kühlbeck]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Gislinde Kühlbeck
Context triple: [Klaus Kinski, spouse, Gislinde Kühlbeck]
  • A. Birgit Menzel
    Birgit Menzel is a scholar and academic known for her work in Slavic studies and Russian literature and culture.
  • B. Birgit Kroencke
    Birgit Kroencke is a Danish former model and painter best known as the longtime wife of British actor Christopher Lee.
  • C. Ulrike Körner
    Ulrike Körner is a person notable enough to be recognized as a prominent bearer of the surname Körner.
  • D. Elisabeth Röckel
    Elisabeth Röckel was a 19th-century German soprano closely associated with the Viennese musical scene and figures such as Beethoven and her husband, composer Johann Nepomuk Hummel.
  • E. Barbara Scholz
    Barbara Scholz is a philosopher of linguistics known for her influential critiques of nativist theories of language acquisition, particularly the poverty of the stimulus argument.
  • 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: Gislinde Kühlbeck
Triple: [Klaus Kinski, spouse, Gislinde Kühlbeck]
Generated description
Gislinde Kühlbeck is known as the spouse of the late German actor Klaus Kinski.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Gislinde Kühlbeck
Target entity description: Gislinde Kühlbeck is known as the spouse of the late German actor Klaus Kinski.
  • A. Birgit Menzel
    Birgit Menzel is a scholar and academic known for her work in Slavic studies and Russian literature and culture.
  • B. Birgit Kroencke
    Birgit Kroencke is a Danish former model and painter best known as the longtime wife of British actor Christopher Lee.
  • C. Ulrike Körner
    Ulrike Körner is a person notable enough to be recognized as a prominent bearer of the surname Körner.
  • D. Elisabeth Röckel
    Elisabeth Röckel was a 19th-century German soprano closely associated with the Viennese musical scene and figures such as Beethoven and her husband, composer Johann Nepomuk Hummel.
  • E. Barbara Scholz
    Barbara Scholz is a philosopher of linguistics known for her influential critiques of nativist theories of language acquisition, particularly the poverty of the stimulus argument.
  • 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_69d8d391eb488190ac2e9abf5bf255e4 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e562e3a6d08190b2409bcbf0c42444 completed April 19, 2026, 11:18 p.m.
NED1 Entity disambiguation (via context triple) batch_6a054706d9a081909e40d1fa35549ead completed May 14, 2026, 3:52 a.m.
NEDg Description generation batch_6a0547f9e1f08190b799cc931edf08d5 completed May 14, 2026, 3:56 a.m.
NED2 Entity disambiguation (via description) batch_6a0548ae7fec8190a8b7196ca4d537c3 completed May 14, 2026, 3:59 a.m.
Created at: April 10, 2026, 11:49 a.m.