Triple

T20878708
Position Surface form Disambiguated ID Type / Status
Subject Great Glass Elevator E514087 entity
Predicate usedByCharacter P31799 FINISHED
Object Grandma Josephine 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: Grandma Josephine | Statement: [Great Glass Elevator, usedByCharacter, Grandma Josephine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Grandma Josephine
Context triple: [Great Glass Elevator, usedByCharacter, Grandma Josephine]
  • A. Grandma Josephine chosen
    Grandma Josephine is one of Charlie Bucket’s elderly, bedridden grandmothers in Roald Dahl’s novel "Charlie and the Chocolate Factory."
  • B. Josephine (grandmother)
    Josephine is the grandmother of Omar Little, a key character in the television series "The Wire."
  • C. Grandmother Spaulding
    Grandmother Spaulding is a warm, wise, and nostalgic figure in Ray Bradbury’s novel "Dandelion Wine," embodying the comforts and traditions of small-town family life.
  • D. Nannie
    Nannie is a feminine given name, often used as a diminutive or variant of names like Nancy or Anne.
  • E. Aunt Louie
    Aunt Louie is a key character in the crime drama series "Snowfall," known as Franklin Saint’s tough, business-savvy aunt who helps build and manage his growing drug empire.
  • 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_69e0b4f733f081908a401c0b7beb0b9f completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c6775f108190a79cd5e8c31cecf6 completed April 21, 2026, 12:36 a.m.
Created at: April 16, 2026, 12:45 p.m.