Triple

T8947006
Position Surface form Disambiguated ID Type / Status
Subject Elizabeth Olsen E213244 entity
Predicate characterPortrayed P1507 FINISHED
Object Scarlet Witch E199163 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: Scarlet Witch | Statement: [Elizabeth Olsen, characterPortrayed, Scarlet Witch]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Scarlet Witch
Context triple: [Elizabeth Olsen, characterPortrayed, Scarlet Witch]
  • A. Scarlet Witch chosen
    Scarlet Witch is a powerful Marvel Comics superhero and Avenger, known for her reality-warping chaos magic and complex moral journey.
  • B. Luna Maximoff
    Luna Maximoff is a Marvel Comics character, the daughter of Quicksilver and Crystal, notable as a human-Inhuman hybrid with empathic abilities.
  • C. Agatha Harkness
    Agatha Harkness is a powerful and cunning witch from Marvel Comics and the Marvel Cinematic Universe, known for manipulating magic and serving as both mentor and antagonist to other magic users like Wanda Maximoff.
  • D. Monica Rambeau
    Monica Rambeau is a Marvel Comics superhero and S.W.O.R.D. agent who gains energy-based powers and becomes a key figure in the Marvel Cinematic Universe.
  • E. Wanda
    Wanda is a feminine given name of Slavic origin, particularly common in Poland and other Central and Eastern European countries.
  • 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_69ca839843408190a39069a029a89f15 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc66deb8ec819087a9c5eddd24c08a completed April 1, 2026, 12:29 a.m.
NED1 Entity disambiguation (via context triple) batch_69d01732bf408190b64ce7687d91a502 completed April 3, 2026, 7:38 p.m.
Created at: March 30, 2026, 6:59 p.m.