Triple

T8494084
Position Surface form Disambiguated ID Type / Status
Subject Slan E201050 entity
Predicate mainCharacter P1183 FINISHED
Object Granny E269712 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: Granny | Statement: [Slan, mainCharacter, Granny]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Granny
Context triple: [Slan, mainCharacter, Granny]
  • A. Granny chosen
    Granny is a recurring elderly character in the Looney Tunes cartoons, best known as the kindly but sharp-witted owner of Tweety Bird (and often Sylvester’s exasperated caretaker).
  • B. Grandma
    Grandma is a character in the voxel-based metaverse game The Sandbox, likely designed as a stylized elderly figure that players can interact with or use in their creations.
  • C. Grandma
    "Grandma" is a 2015 American comedy-drama film starring Lily Tomlin as an irascible poet helping her granddaughter, featuring Laverne Cox in a supporting role.
  • D. Grandma
    Grandma is a key supporting character in the 2020 dark fantasy film "The Witches," serving as the wise and protective guardian who helps her grandson confront a secret society of child-hating witches.
  • E. Miss Granny
    Miss Granny is a popular South Korean comedy-drama film about an elderly woman who mysteriously regains her youthful appearance, leading to humorous and heartfelt consequences.
  • 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_69ca831ee390819095fae73400bbfafc completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe579b7088190b297b04527e36a2b completed March 31, 2026, 3:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69ce3a5c260c8190bc7012a04363d260 completed April 2, 2026, 9:43 a.m.
Created at: March 30, 2026, 6:13 p.m.