Triple

T19452512
Position Surface form Disambiguated ID Type / Status
Subject Buz Kohan E486646 entity
Predicate spouse P13 FINISHED
Object Ruzena Kohan
Ruzena Kohan is known as the wife of American television writer and producer Buz Kohan.
 E1377569 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: Ruzena Kohan | Statement: [Buz Kohan, spouse, Ruzena Kohan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Ruzena Kohan
Context triple: [Buz Kohan, spouse, Ruzena Kohan]
  • A. Renata Kallosh
    Renata Kallosh is a theoretical physicist known for her influential work in supergravity, string theory, and cosmology.
  • B. Helena Krywaniuk
    Helena Krywaniuk is a pharmacy professional associated with Eagle Pharmacy, likely working in a clinical or community pharmacy role.
  • C. Danuta Stenka
    Danuta Stenka is a renowned Polish film, television, and theatre actress known for her powerful dramatic roles and extensive work in Polish cinema.
  • D. Nena Danevic
    Nena Danevic is a film editor best known for her Academy Award–winning work on the 1984 historical drama "Amadeus."
  • E. Myrteza Ali Struga
    Myrteza Ali Struga was an Albanian nationalist figure known for his role in the country’s independence movement as a signatory of the 1912 Vlora Declaration.
  • 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: Ruzena Kohan
Triple: [Buz Kohan, spouse, Ruzena Kohan]
Generated description
Ruzena Kohan is known as the wife of American television writer and producer Buz Kohan.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Ruzena Kohan
Target entity description: Ruzena Kohan is known as the wife of American television writer and producer Buz Kohan.
  • A. Renata Kallosh
    Renata Kallosh is a theoretical physicist known for her influential work in supergravity, string theory, and cosmology.
  • B. Helena Krywaniuk
    Helena Krywaniuk is a pharmacy professional associated with Eagle Pharmacy, likely working in a clinical or community pharmacy role.
  • C. Danuta Stenka
    Danuta Stenka is a renowned Polish film, television, and theatre actress known for her powerful dramatic roles and extensive work in Polish cinema.
  • D. Nena Danevic
    Nena Danevic is a film editor best known for her Academy Award–winning work on the 1984 historical drama "Amadeus."
  • E. Myrteza Ali Struga
    Myrteza Ali Struga was an Albanian nationalist figure known for his role in the country’s independence movement as a signatory of the 1912 Vlora Declaration.
  • 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_69d8e8d86d608190bd199a98d0297f27 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e63392aab08190aab09b7c356e5b10 completed April 20, 2026, 2:09 p.m.
NED1 Entity disambiguation (via context triple) batch_6a073b33395081909ac7e5406843da5c completed May 15, 2026, 3:26 p.m.
NEDg Description generation batch_6a073ba7f03481908ed5c06a46c0a029 completed May 15, 2026, 3:28 p.m.
NED2 Entity disambiguation (via description) batch_6a073cae2df481908ed9a0ee0bc14fd5 completed May 15, 2026, 3:33 p.m.
Created at: April 10, 2026, 1:38 p.m.