Triple

T16064508
Position Surface form Disambiguated ID Type / Status
Subject Dafne Keen E389698 entity
Predicate name P16 FINISHED
Object Dafne Keen E389698 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: Dafne Keen | Statement: [Dafne Keen, name, Dafne Keen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dafne Keen
Context triple: [Dafne Keen, name, Dafne Keen]
  • A. Dafne Keen chosen
    Dafne Keen is a British-Spanish actress best known for her breakout role as Laura/X-23 in the film "Logan" and for playing Lyra Belacqua in the television adaptation of "His Dark Materials."
  • B. Sasha Calle
    Sasha Calle is an American actress best known for playing Supergirl in the 2023 DC superhero film "The Flash."
  • C. Mia Kirshner
    Mia Kirshner is a Canadian actress known for her dark, nuanced performances in film and television, including her notable role in the crime drama "The Black Dahlia."
  • D. Samara Weaving
    Samara Weaving is an Australian actress known for her roles in film and television, particularly in horror-comedy and thriller projects such as "Ready or Not" and "The Babysitter."
  • E. Maggie Jacobs
    Maggie Jacobs is a fictional, socially awkward and fame-obsessed aspiring actress portrayed by Ashley Jensen in the British television comedy series "Extras."
  • 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_69d86daf32ec8190a8c0466c8f49c3c0 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1837b048881908326739bbede756f completed April 17, 2026, 12:48 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffe47ef6648190bf1fe216e78ef660 completed May 10, 2026, 1:50 a.m.
Created at: April 10, 2026, 4:57 a.m.