Triple

T14806874
Position Surface form Disambiguated ID Type / Status
Subject Jimmy Smits E348059 entity
Predicate partner P1136 FINISHED
Object Wanda De Jesus E348063 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: Wanda De Jesus | Statement: [Jimmy Smits, partner, Wanda De Jesus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Wanda De Jesus
Context triple: [Jimmy Smits, partner, Wanda De Jesus]
  • A. Wanda De Jesus chosen
    Wanda De Jesus is an American actress known for her roles in television series such as "Santa Barbara," "CSI: Miami," and "Sons of Anarchy."
  • B. Elvera Sanchez
    Elvera Sanchez was an American dancer and vaudeville performer best known as the mother of entertainer Sammy Davis Jr.
  • C. Magda Ramirez
    Magda Ramirez is the central protagonist of the television drama series "The Division," around whom the show's primary storylines and character developments revolve.
  • D. Alma Moreno
    Alma Moreno is a Filipino actress, comedian, and former sex symbol who became a prominent television personality and later entered politics.
  • E. Mabel Mora
    Mabel Mora is a sharp-witted, enigmatic young woman and true-crime enthusiast who becomes one of the central amateur sleuths investigating murders in the comedy-mystery series "Only Murders in the Building."
  • 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_69d822ea8b7c819097dfadf3d45545e6 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69decf33b6a08190ab6a4cfeda2cc09c completed April 14, 2026, 11:35 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe24c8bc6881908736c029943997ae completed May 8, 2026, 6 p.m.
Created at: April 10, 2026, 1:40 a.m.