Triple

T10457513
Position Surface form Disambiguated ID Type / Status
Subject Love Liza E246583 entity
Predicate hasSpouseCharacter P33561 FINISHED
Object Liza E246583 NE FINISHED

How this triple was built (3 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: [Love Liza, hasSpouseCharacter, Liza]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Liza
Context triple: [Love Liza, hasSpouseCharacter, Liza]
  • A. Liza
    Liza is a feminine given name most famously associated with American actress and singer Liza Minnelli.
  • B. 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.
  • C. Love Liza chosen
    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.
  • D. Liza Rey
    Liza Rey is a musician and harpist known for her work in jazz and popular music, as well as for being part of a prominent musical family.
  • E. Liz
    Liz is a common shortened form or nickname for the given name Elizabeth.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasSpouseCharacter
Context triple: [Love Liza, hasSpouseCharacter, Liza]
  • A. hasSpouseInStory
    Indicates that one entity is depicted as the spouse of another within the context of a particular story or narrative.
  • B. hasNamesakeSpouse
    Indicates that one entity has a spouse who shares the same name as another specified entity.
  • C. spouseAssociatedWith chosen
    Indicates a marital or spousal relationship or close association between two entities.
  • D. hasAuthorSpouse
    Indicates that the spouse of the subject entity is the author of the related work or entity.
  • E. spouseCharacteristic
    Indicates that a particular characteristic, trait, or attribute is associated with a person’s spouse within the relationship.
  • F. None of above.

Provenance (4 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_69d381c04fe08190957c26c526a3b05a completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4fe4a56e08190ab56d762d6a91b01 completed April 7, 2026, 12:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69d89fbf3a308190af6b605ce781396a completed April 10, 2026, 6:59 a.m.
PD Predicate disambiguation batch_69d4fb7d353c8190a73f439a956c7606 completed April 7, 2026, 12:41 p.m.
Created at: April 6, 2026, 12:18 p.m.