Triple

T21744229
Position Surface form Disambiguated ID Type / Status
Subject Mark-Paul Gosselaar E536742 entity
Predicate spouse P13 FINISHED
Object Lisa Ann Russell 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: Lisa Ann Russell | Statement: [Mark-Paul Gosselaar, spouse, Lisa Ann Russell]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lisa Ann Russell
Context triple: [Mark-Paul Gosselaar, spouse, Lisa Ann Russell]
  • A. Lisa Ann Russell chosen
    Lisa Ann Russell is an American former model and actress who has appeared in film and television and is known for her marriages to actor Mark-Paul Gosselaar and television host Jeff Probst.
  • B. Lisa Ann Walter
    Lisa Ann Walter is an American actress and comedian best known for her roles in films like "The Parent Trap" (1998) and the TV series "Abbott Elementary."
  • C. Denise Kaufman
    Denise Kaufman is an American musician and yoga teacher best known as a founding member of the 1960s all-female rock band Ace of Cups.
  • D. Lisa Ann Sandell
    Lisa Ann Sandell is an American author and editor best known for her young adult novels and work in children’s publishing.
  • E. Lisa Ann Cooper
    Lisa Ann Cooper is known primarily for her past marriage to American actor Chris Sarandon.
  • 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_69e0c46df5448190b4322127ffc4c690 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69f01a75352c8190bcd46759562ee251 completed April 28, 2026, 2:24 a.m.
Created at: April 16, 2026, 6:49 p.m.