Triple

T22795528
Position Surface form Disambiguated ID Type / Status
Subject Jean Lyndsey Torren Marsh E564230 entity
Predicate portrayed P1668 FINISHED
Object Queen Bavmorda 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: Queen Bavmorda | Statement: [Jean Lyndsey Torren Marsh, portrayed, Queen Bavmorda]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Queen Bavmorda
Context triple: [Jean Lyndsey Torren Marsh, portrayed, Queen Bavmorda]
  • A. Queen Bavmorda chosen
    Queen Bavmorda is the ruthless and power-hungry sorceress-queen who serves as the primary villain in the fantasy film "Willow."
  • B. Queen Sitre
    Queen Sitre was an ancient Egyptian queen, likely a royal consort of the New Kingdom period, known from her dedicated tomb and associated funerary monuments.
  • C. Bavmorda
    Bavmorda is the primary villain and powerful sorceress queen in the fantasy film "Willow."
  • D. Tamora
    Tamora is the vengeful Queen of the Goths and a central antagonist in William Shakespeare’s tragedy "Titus Andronicus."
  • E. Grimelda
    Grimelda was a medieval Hungarian noblewoman, traditionally identified as a daughter of King Géza of Hungary and known for her dynastic marriage into the Venetian ruling family.
  • 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_69e2458185f88190b0045227ee420411 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17cd8e0c4819086da0488bea56a34 completed April 29, 2026, 3:36 a.m.
Created at: April 17, 2026, 3:30 p.m.