Triple

T5321070
Position Surface form Disambiguated ID Type / Status
Subject Jaylah E121673 entity
Predicate portrayedBy P1507 FINISHED
Object Sofia Boutella E48820 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: Sofia Boutella | Statement: [Jaylah, portrayedBy, Sofia Boutella]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sofia Boutella
Context triple: [Jaylah, portrayedBy, Sofia Boutella]
  • A. Sofia Boutella chosen
    Sofia Boutella is an Algerian-French dancer and actress known for her dynamic action roles in films such as "Kingsman: The Secret Service," "Star Trek Beyond," and "The Mummy."
  • B. Bérénice Marlohe
    Bérénice Marlohe is a French actress best known internationally for her role as Sévérine in the James Bond film "Skyfall."
  • C. Safy Boutella
    Safy Boutella is an Algerian musician and composer known for his influential role in modern Algerian music and film scores.
  • D. Lea Seydoux
    Léa Seydoux is a French actress known for her roles in films such as "Blue Is the Warmest Colour," multiple James Bond movies, and various international arthouse and blockbuster productions.
  • E. Ana de Armas
    Ana de Armas is a Cuban-Spanish actress known for her breakout roles in films such as "Blade Runner 2049," "Knives Out," and "Blonde."
  • 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_69bd463d956c819088105c3db802c017 completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd85761ec48190879210af116ed8b9 completed March 20, 2026, 5:35 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf18a4dff48190bce18f0106c7a8e7 completed March 21, 2026, 10:16 p.m.
Created at: March 20, 2026, 1:59 p.m.