Triple

T20389621
Position Surface form Disambiguated ID Type / Status
Subject Lars and the Real Girl E498051 entity
Predicate starring P1507 FINISHED
Object Kelli Garner 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: Kelli Garner | Statement: [Lars and the Real Girl, starring, Kelli Garner]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kelli Garner
Context triple: [Lars and the Real Girl, starring, Kelli Garner]
  • A. Kelli Garner chosen
    Kelli Garner is an American actress known for her work in independent films and television, including notable roles in projects like "Lars and the Real Girl" and the miniseries "The Secret Life of Marilyn Monroe."
  • B. Debra McMichael
    Debra McMichael is an American former professional wrestling valet, manager, and occasional wrestler best known for her appearances in WWE and WCW during the late 1990s and early 2000s.
  • C. Tracy Garner
    Tracy Garner is known as the spouse of Doug Billings, a character from the comedy film series "The Hangover."
  • D. Yvette Marie Stevens
    Yvette Marie Stevens is the birth name of Chaka Khan, the iconic American singer known as the "Queen of Funk."
  • E. Gina Matthews
    Gina Matthews is a film and television producer best known for her work on popular romantic comedies such as "13 Going on 30."
  • 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_69e0b4a71ebc8190b153a36c738730f4 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6790e65a081909832855758fffd14 completed April 20, 2026, 7:05 p.m.
Created at: April 16, 2026, 11:28 a.m.