Triple

T7828998
Position Surface form Disambiguated ID Type / Status
Subject Gianna Bryant E181317 entity
Predicate sibling P363 FINISHED
Object Natalia Bryant E241063 NE FINISHED

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: Natalia Bryant | Statement: [Gianna Bryant, sibling, Natalia Bryant]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Natalia Bryant
Context triple: [Gianna Bryant, sibling, Natalia Bryant]
  • A. Natalia Bryant chosen
    Natalia Bryant is an American model and the eldest daughter of the late NBA legend Kobe Bryant and Vanessa Bryant.
  • B. Nicole Johnson
    Nicole Johnson is an American model and former Miss California USA best known as the wife of Olympic swimmer Michael Phelps.
  • C. Nicole Watterson
    Nicole Watterson is a hardworking, hot-tempered blue cat mother in the animated series "The Amazing World of Gumball," known for her fierce competitiveness and deep love for her family.
  • D. Nikki Butler
    Nikki Butler is an American fashion designer best known for her long-term marriage to English actor Tim Roth.
  • E. Lulamae Barnes
    Lulamae Barnes is the birth name of Holly Golightly, the iconic, free-spirited socialite from Truman Capote’s novella and the film "Breakfast at Tiffany’s."
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69ca8282ccec819083c48efb72d21cf9 completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cb04aaed1881908e1da129a43ef9c7 completed March 30, 2026, 11:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69cb14b955488190a4ce0178d84d1dc6 completed March 31, 2026, 12:26 a.m.
Created at: March 30, 2026, 4:44 p.m.