Triple

T16516920
Position Surface form Disambiguated ID Type / Status
Subject Conrad Kain E401206 entity
Predicate spouse P13 FINISHED
Object Berthe Kain
Berthe Kain was the wife of renowned Austrian-Canadian mountaineer and mountain guide Conrad Kain.
E1229864 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: Berthe Kain | Statement: [Conrad Kain, spouse, Berthe Kain]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Berthe Kain
Context triple: [Conrad Kain, spouse, Berthe Kain]
  • A. Léonie Cassel
    Léonie Cassel is the younger daughter of Italian actress and model Monica Bellucci and French actor Vincent Cassel.
  • B. Fernande Barrey
    Fernande Barrey was a French artist’s model and painter active in early 20th-century Paris, known for her connections to the Montparnasse artistic milieu.
  • C. Marie Lelay
    Marie Lelay is a French television journalist and one of the three central protagonists in the supernatural drama film "Hereafter."
  • D. Odile Decq
    Odile Decq is a renowned French architect and urban planner known for her bold, avant-garde designs and influential role in contemporary architecture.
  • E. Marceline Hugot
    Marceline Hugot is an American character actress known for her supporting roles in film, television, and theater, often portraying quirky or offbeat characters.
  • 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: Berthe Kain
Triple: [Conrad Kain, spouse, Berthe Kain]
Generated description
Berthe Kain was the wife of renowned Austrian-Canadian mountaineer and mountain guide Conrad Kain.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Berthe Kain
Target entity description: Berthe Kain was the wife of renowned Austrian-Canadian mountaineer and mountain guide Conrad Kain.
  • A. Léonie Cassel
    Léonie Cassel is the younger daughter of Italian actress and model Monica Bellucci and French actor Vincent Cassel.
  • B. Fernande Barrey
    Fernande Barrey was a French artist’s model and painter active in early 20th-century Paris, known for her connections to the Montparnasse artistic milieu.
  • C. Marie Lelay
    Marie Lelay is a French television journalist and one of the three central protagonists in the supernatural drama film "Hereafter."
  • D. Odile Decq
    Odile Decq is a renowned French architect and urban planner known for her bold, avant-garde designs and influential role in contemporary architecture.
  • E. Marceline Hugot
    Marceline Hugot is an American character actress known for her supporting roles in film, television, and theater, often portraying quirky or offbeat characters.
  • 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_69d883838abc8190bc79cb2d41733ce2 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e32e7c7e588190acbcc2b807a98909 completed April 18, 2026, 7:10 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0091872e648190b805aa4e41bcbb6d completed May 10, 2026, 2:09 p.m.
NEDg Description generation batch_6a009a013ccc81908becd542b2f12e8f completed May 10, 2026, 2:45 p.m.
NED2 Entity disambiguation (via description) batch_6a009abdf55081908976fa9f9752a447 completed May 10, 2026, 2:48 p.m.
Created at: April 10, 2026, 5:14 a.m.