Triple

T22640753
Position Surface form Disambiguated ID Type / Status
Subject Liza Snyder E558817 entity
Predicate givenName P17 FINISHED
Object Liza 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: Liza | Statement: [Liza Snyder, givenName, Liza]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Liza
Context triple: [Liza Snyder, givenName, Liza]
  • A. Liza chosen
    Liza is a feminine given name most famously associated with American actress and singer Liza Minnelli.
  • B. Liza
    Liza is a young, impoverished prostitute in Dostoevsky’s "Notes from Underground" whose encounter with the narrator exposes themes of vulnerability, dignity, and moral awakening.
  • C. Liza
    Liza is a central tragic heroine in Alexander Pushkin’s short story "The Queen of Spades," whose ill-fated love and entanglement with gambling intrigue drive much of the plot.
  • D. Love Liza
    Love Liza is a 2002 independent drama film starring Philip Seymour Hoffman as a grieving widower spiraling into gasoline huffing after his wife's suicide.
  • E. Liza Miller
    Liza Miller is the 40-year-old divorced mother who pretends to be in her twenties to restart her publishing career in the TV series "Younger."
  • 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_69e24547f7fc819086e2c4ba3b979657 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f170116fe881908178cffef26e3ae7 completed April 29, 2026, 2:42 a.m.
Created at: April 17, 2026, 3:04 p.m.