Triple

T8450952
Position Surface form Disambiguated ID Type / Status
Subject Okja E199795 entity
Predicate stars P1956 FINISHED
Object Lily Collins E435012 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: Lily Collins | Statement: [Okja, stars, Lily Collins]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lily Collins
Context triple: [Okja, stars, Lily Collins]
  • A. Lily Collins chosen
    Lily Collins is a British-American actress and model known for roles in films like "Mirror Mirror" and the series "Emily in Paris."
  • B. Sophia Di Martino
    Sophia Di Martino is a British actress best known for her role as Sylvie in the Marvel series "Loki" and for appearances in films and television including the romantic comedy "Yesterday."
  • C. 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."
  • D. Lily Houghton
    Lily Houghton is a fictional, adventurous British botanist and explorer from the film "Jungle Cruise."
  • E. Lily James
    Lily James is an English actress known for her roles in films such as Cinderella, Baby Driver, and Mamma Mia! Here We Go Again, as well as the TV series Downton Abbey.
  • 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_69ca8318231881908fd1bc1c4d45d286 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe44815488190a912d63512e19af0 completed March 31, 2026, 3:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69ce6cf9368081909cad61cdf6156a0e completed April 2, 2026, 1:19 p.m.
Created at: March 30, 2026, 6:09 p.m.