Triple

T13849560
Position Surface form Disambiguated ID Type / Status
Subject Miguel Ferrer E332897 entity
Predicate spouse P13 FINISHED
Object Leilani Sarelle E392064 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: Leilani Sarelle | Statement: [Miguel Ferrer, spouse, Leilani Sarelle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Leilani Sarelle
Context triple: [Miguel Ferrer, spouse, Leilani Sarelle]
  • A. Leilani Sarelle chosen
    Leilani Sarelle is an American actress best known for her role as Roxy in the 1992 thriller film "Basic Instinct."
  • B. Rachel Ramras
    Rachel Ramras is an American actress, comedian, and voice artist known for her work on animated series such as "The Looney Tunes Show" and for co-creating and starring in the comedy series "Nobodies."
  • C. Jacelyn Reeves
    Jacelyn Reeves is an American former flight attendant best known as the mother of actor Scott Eastwood and for her past relationship with Clint Eastwood.
  • D. Leilani Mitchell
    Leilani Mitchell is an American-Australian professional basketball player and point guard known for her sharpshooting and playmaking in the WNBA and international competition.
  • E. Rochelle Aytes
    Rochelle Aytes is an American actress known for her roles in television series such as "Mistresses" and "The Purge," as well as films like "Trick 'r Treat."
  • 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_69d81c5ba13c8190839315f54768acfd completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de02d8fb788190baef7537be2baecb completed April 14, 2026, 9:03 a.m.
NED1 Entity disambiguation (via context triple) batch_69fdd5b719848190981aec627d64df58 completed May 8, 2026, 12:23 p.m.
Created at: April 9, 2026, 10:14 p.m.