Triple

T21528788
Position Surface form Disambiguated ID Type / Status
Subject Freddie Thorp E531173 entity
Predicate coStarredWith P14987 FINISHED
Object Gaia Weiss 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: Gaia Weiss | Statement: [Freddie Thorp, coStarredWith, Gaia Weiss]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gaia Weiss
Context triple: [Freddie Thorp, coStarredWith, Gaia Weiss]
  • A. Gaia Weiss chosen
    Gaia Weiss is a French actress and model known for her roles in films and television series such as "Vikings" and various European productions.
  • B. Gemma Donati
    Gemma Donati was the Florentine noblewoman who became the wife of the Italian poet Dante Alighieri.
  • C. Daria Cassini
    Daria Cassini was the daughter of American actress Gene Tierney and fashion designer Oleg Cassini, known largely for her parents’ Hollywood and couture legacies.
  • D. Athene Seyler
    Athene Seyler was a distinguished English character actress known for her long stage and film career, often portraying eccentric or comedic older women.
  • E. Zoe Moon
    Zoe Moon is the central protagonist of the sitcom "Zoe Ever After," a newly single mother navigating life, love, and career after divorce.
  • 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_69e0c45e5b8881908ac18fc2f493b114 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ee8852e68c8190a5341c9f75081382 completed April 26, 2026, 9:49 p.m.
Created at: April 16, 2026, 6:27 p.m.