Triple

T4884749
Position Surface form Disambiguated ID Type / Status
Subject Wyatt Earp E109411 entity
Predicate starring P1507 FINISHED
Object Isabella Rossellini E96977 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: Isabella Rossellini | Statement: [Wyatt Earp, starring, Isabella Rossellini]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Isabella Rossellini
Context triple: [Wyatt Earp, starring, Isabella Rossellini]
  • A. Isabella Rossellini chosen
    Isabella Rossellini is an Italian-American actress, model, and filmmaker known for her roles in films like "Blue Velvet" and "Death Becomes Her" and for her work as a Lancôme spokesmodel.
  • B. Ingrid Rossellini
    Ingrid Rossellini is the daughter of Italian film director Roberto Rossellini and is associated with the prominent Rossellini cinematic family.
  • C. Monica Bellucci
    Monica Bellucci is an Italian actress and model known for her work in European cinema and major Hollywood films, including roles in The Matrix series, Malèna, and various James Bond and arthouse productions.
  • D. Greta Favino
    Greta Favino is the daughter of acclaimed Italian actor Pierfrancesco Favino.
  • E. Rita Rossi
    Rita Rossi is the birth name of Rita R. Colwell, an American microbiologist and former director of the U.S. National Science Foundation known for her research on cholera and marine microbes.
  • 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_69bd440f71348190b99938e59fb7f9a1 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd6de3718881908521968fa6e6b444 completed March 20, 2026, 3:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69be680bf12c8190a5da2c7f0088cec2 completed March 21, 2026, 9:42 a.m.
Created at: March 20, 2026, 1:27 p.m.