Triple

T14358551
Position Surface form Disambiguated ID Type / Status
Subject The Perfect Guy E356035 entity
Predicate castMember P1668 FINISHED
Object Sanaa Lathan E31721 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: Sanaa Lathan | Statement: [The Perfect Guy, castMember, Sanaa Lathan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sanaa Lathan
Context triple: [The Perfect Guy, castMember, Sanaa Lathan]
  • A. Sanaa Lathan chosen
    Sanaa Lathan is an American actress known for her work in film, television, and voice acting, including prominent roles in movies like "Love & Basketball" and "Brown Sugar."
  • B. Jordana Brewster
    Jordana Brewster is a Panamanian-American actress best known for her role as Mia Toretto in the Fast & Furious film franchise.
  • C. Angelica Bullock
    Angelica Bullock is the eccentric, status-conscious matriarch of the wealthy Bullock family in the classic screwball comedy film "My Man Godfrey."
  • D. Deva Cassel
    Deva Cassel is an Italian model and emerging actress, known as the daughter of Monica Bellucci and Vincent Cassel.
  • E. Michelle Rodriguez
    Michelle Rodriguez is an American actress best known for her tough, action-oriented roles, particularly as Letty Ortiz in the Fast & Furious film franchise.
  • 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_69d82790a7e08190877e2d349b2e8d8e completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de8f52ca7881908704eef20228aed3 completed April 14, 2026, 7:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd7a3479088190929ab4b9d218a608 completed May 8, 2026, 5:52 a.m.
Created at: April 10, 2026, 1:15 a.m.