Triple

T7023911
Position Surface form Disambiguated ID Type / Status
Subject Kobe Bryant E162894 entity
Predicate spouse P13 FINISHED
Object Vanessa Bryant E162894 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: Vanessa Bryant | Statement: [Kobe Bryant, spouse, Vanessa Bryant]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Vanessa Bryant
Context triple: [Kobe Bryant, spouse, Vanessa Bryant]
  • A. Vanessa Bryant chosen
    Vanessa Bryant is an American philanthropist and businesswoman best known as the widow of NBA legend Kobe Bryant and co-founder of the Mamba & Mambacita Sports Foundation.
  • B. Gianna Bryant
    Gianna Bryant was the teenage daughter of NBA legend Kobe Bryant and a promising young basketball player whose life was tragically cut short in a 2020 helicopter crash.
  • C. Capri Bryant
    Capri Bryant is the youngest daughter of late NBA legend Kobe Bryant and his wife Vanessa Bryant.
  • D. Whitney Phelps
    Whitney Phelps is the older sister of American Olympic swimming legend Michael Phelps and a former competitive swimmer herself.
  • E. Katie Bryant
    Katie Bryant is known as the daughter of Phil Bryant, the former governor of Mississippi.
  • 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_69c6885b26248190a857541e3d10e299 completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6e1fa043c81909c900e394a5972f9 completed March 27, 2026, 8 p.m.
NED1 Entity disambiguation (via context triple) batch_69c78857d23c8190904a90459a802cb8 completed March 28, 2026, 7:50 a.m.
Created at: March 27, 2026, 2:35 p.m.