Triple

T20818430
Position Surface form Disambiguated ID Type / Status
Subject Hoggle E512506 entity
Predicate portrayedBy P1507 FINISHED
Object Shari Weiser 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: Shari Weiser | Statement: [Hoggle, portrayedBy, Shari Weiser]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Shari Weiser
Context triple: [Hoggle, portrayedBy, Shari Weiser]
  • A. Shari Weiser chosen
    Shari Weiser is a puppeteer and performer best known for physically portraying the character Hoggle in Jim Henson’s fantasy film "Labyrinth."
  • B. Shari McMahan
    Shari McMahan is an American academic administrator and former provost who serves as the president of Eastern Washington University.
  • C. Julie Weiss
    Julie Weiss is an acclaimed American costume designer known for her work in film, television, and theater, including multiple Academy Award–nominated productions.
  • D. Deborah Schindler
    Deborah Schindler is a film producer best known for her work on the 2003 drama "Mona Lisa Smile."
  • E. Susan Weiler
    Susan Weiler is a prominent landscape architect and design leader known for her influential work with the firm OLIN on major public and urban spaces.
  • 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_69e0b4cd25088190b48ca9700cd24efc completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c2f5b1e08190a9c26f76bd544b68 completed April 21, 2026, 12:21 a.m.
Created at: April 16, 2026, 12:41 p.m.