Triple

T19452464
Position Surface form Disambiguated ID Type / Status
Subject Jenji Kohan E486645 entity
Predicate parent P120 FINISHED
Object Buz Kohan NE NERFINISHED

How this triple was built (2 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: Buz Kohan | Statement: [Jenji Kohan, parent, Buz Kohan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Buz Kohan
Context triple: [Jenji Kohan, parent, Buz Kohan]
  • A. Buz Kohan chosen
    Buz Kohan is an American television writer, producer, and composer known for his work on variety shows and specials.
  • B. Bobby Khan
    Bobby Khan is an Indian film director and choreographer known for his work in Bollywood music videos and films.
  • C. Ed Dumani
    Ed Dumani is a central crime boss and strategist in the British television series "Gangs of London," known for his pivotal role in the city's criminal underworld and complex family loyalties.
  • D. Kenan Kong
    Kenan Kong is a Chinese teenager who becomes the superhero New Super-Man in DC Comics after gaining powers similar to Superman.
  • E. Ali Kiba
    Ali Kiba is a Tanzanian singer and songwriter known as one of East Africa’s leading Bongo Flava artists.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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.
Created at: April 10, 2026, 1:38 p.m.