Triple

T19879648
Position Surface form Disambiguated ID Type / Status
Subject Ennis Cosby E477733 entity
Predicate sibling P363 FINISHED
Object Evin Cosby 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: Evin Cosby | Statement: [Ennis Cosby, sibling, Evin Cosby]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Evin Cosby
Context triple: [Ennis Cosby, sibling, Evin Cosby]
  • A. Evin Cosby chosen
    Evin Cosby is the daughter of comedian Bill Cosby, known for her work as a boutique owner and for occasionally speaking publicly about her family.
  • B. Tyree Pittman
    Tyree Pittman, better known as Young Chop, is an American record producer and rapper recognized for shaping the sound of Chicago drill music.
  • C. Andrew Cosby
    Andrew Cosby is an American comic book writer, screenwriter, and producer best known for co-creating the science fiction television series "Eureka."
  • D. Trenton Hassell
    Trenton Hassell is a former professional basketball player best known for his NBA career as a versatile defensive-minded wing.
  • E. Russel Hines
    Russel Hines is a fictional character in the darkly comedic crime film "To Die For."
  • 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_69d8e51f32b08190b3687f4f60353250 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e658dd869c81908aed91ee767f5f3d completed April 20, 2026, 4:48 p.m.
Created at: April 10, 2026, 1:52 p.m.