Triple

T16892589
Position Surface form Disambiguated ID Type / Status
Subject Chance Combs E424211 entity
Predicate relative P37 FINISHED
Object Kim Porter 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: Kim Porter | Statement: [Chance Combs, relative, Kim Porter]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kim Porter
Context triple: [Chance Combs, relative, Kim Porter]
  • A. Kim Porter chosen
    Kim Porter was an American model and actress best known for her longtime relationship with Sean "Diddy" Combs and her work in fashion and entertainment.
  • B. Laura Porter
    Laura Porter is a central character in the young adult novel "Watch Over Me," around whom the story’s emotional and psychological journey revolves.
  • C. Hilary Farr
    Hilary Farr is a British-Canadian designer and television personality best known as the co-host and home renovation expert on the HGTV series "Love It or List It."
  • D. Lori Marshall
    Lori Marshall is an American television writer and author, known for her work on sitcoms and for collaborating on books about and with her father, filmmaker Garry Marshall.
  • E. Christine Forrest
    Christine Forrest is an American actress and producer best known for her long-time collaboration and marriage with horror filmmaker George A. Romero.
  • 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_69d889da3e8c8190a2b118f383f0beac completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e3bbc6b97c8190b18aca477d6ef647 completed April 18, 2026, 5:13 p.m.
Created at: April 10, 2026, 5:29 a.m.