Triple

T20632808
Position Surface form Disambiguated ID Type / Status
Subject Guardians of the Galaxy Vol. 3 E506999 entity
Predicate portrayedBy P1507 FINISHED
Object Karen Gillan 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: Karen Gillan | Statement: [Guardians of the Galaxy Vol. 3, portrayedBy, Karen Gillan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Karen Gillan
Context triple: [Guardians of the Galaxy Vol. 3, portrayedBy, Karen Gillan]
  • A. Karen Gillan chosen
    Karen Gillan is a Scottish actress and filmmaker best known for her roles as Nebula in the Marvel Cinematic Universe and Amy Pond in the television series Doctor Who.
  • B. Kate Fisher
    Kate Fisher is the mother of American singer and actor Eddie Fisher.
  • C. Felicity Jones
    Felicity Jones is an English actress known for her roles in films such as "The Theory of Everything" and "Rogue One: A Star Wars Story."
  • D. Tamsin Egerton
    Tamsin Egerton is an English actress and model known for roles in films such as "St Trinian's," "Keeping Mum," and "The Look of Love."
  • E. Laura Bailey
    Laura Bailey is an acclaimed American voice actress known for her prominent roles in video games and animation, including award-winning performances in major titles.
  • 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_69e0b4bd4a0081908d4e97a590a33fb2 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6ad0bdcd88190a59d68e03370b271 completed April 20, 2026, 10:47 p.m.
Created at: April 16, 2026, 11:42 a.m.