Triple

T8433494
Position Surface form Disambiguated ID Type / Status
Subject Mantis E199170 entity
Predicate portrayedBy P1507 FINISHED
Object Pom Klementieff E256909 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: Pom Klementieff | Statement: [Mantis, portrayedBy, Pom Klementieff]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pom Klementieff
Context triple: [Mantis, portrayedBy, Pom Klementieff]
  • A. Pom Klementieff chosen
    Pom Klementieff is a French actress best known for playing Mantis in the Marvel Cinematic Universe films.
  • B. Nikita Dragun
    Nikita Dragun is a transgender beauty influencer, YouTuber, and entrepreneur known for her makeup content and cosmetics brand Dragun Beauty.
  • C. Svetlana Khodchenkova
    Svetlana Khodchenkova is a Russian film and television actress known internationally for roles in movies such as "Tinker Tailor Soldier Spy" and "The Wolverine."
  • D. Alexis Mdivani
    Alexis Mdivani was a Georgian-born aristocrat and member of the socially prominent "Marrying Mdivanis," known for his high-profile marriage into great wealth and status.
  • E. Tasya van Ree
    Tasya van Ree is an American artist and photographer known for her black-and-white portraits and conceptual work, as well as her involvement in the Los Angeles art scene.
  • 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_69ca8313c99081909a5c6d83b91de5b3 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbd1a74d948190abd76e7a6efb42ec completed March 31, 2026, 1:52 p.m.
NED1 Entity disambiguation (via context triple) batch_69ce1d673ed48190abf765c203ed2a0f completed April 2, 2026, 7:40 a.m.
Created at: March 30, 2026, 6:07 p.m.