Triple

T19509295
Position Surface form Disambiguated ID Type / Status
Subject Heather Dunbar E488103 entity
Predicate portrayedBy P1507 FINISHED
Object Elizabeth Marvel 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: Elizabeth Marvel | Statement: [Heather Dunbar, portrayedBy, Elizabeth Marvel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Elizabeth Marvel
Context triple: [Heather Dunbar, portrayedBy, Elizabeth Marvel]
  • A. Elizabeth Marvel chosen
    Elizabeth Marvel is an American actress known for her versatile performances in film, television, and theater, including prominent roles in series like Homeland and House of Cards.
  • B. Amy Ruck
    Amy Ruck was the wife of botanist Francis Darwin, son of Charles Darwin, and a member of the extended Darwin family circle in late 19th-century England.
  • C. Melissa Cobb
    Melissa Cobb is an American film producer best known for her work on major animated features, including the Kung Fu Panda franchise.
  • D. Beth Riesgraf
    Beth Riesgraf is an American actress best known for playing the quirky thief Parker on the television series "Leverage."
  • E. Lynn Collins
    Lynn Collins is an American actress known for her roles in films such as X-Men Origins: Wolverine and John Carter, as well as various television series.
  • 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_69d8e8d9d1c88190b01cd78b8be49384 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e6351426448190aec1ee26c09faa24 completed April 20, 2026, 2:15 p.m.
Created at: April 10, 2026, 1:40 p.m.