Triple

T21300835
Position Surface form Disambiguated ID Type / Status
Subject Jessica Sula E525056 entity
Predicate name P16 FINISHED
Object Jessica Sula 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: Jessica Sula | Statement: [Jessica Sula, name, Jessica Sula]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jessica Sula
Context triple: [Jessica Sula, name, Jessica Sula]
  • A. Jessica Sula chosen
    Jessica Sula is a Welsh actress best known for her roles in the British teen drama "Skins" and various American film and television projects.
  • B. Briana DeJesus
    Briana DeJesus is a reality television personality best known for chronicling her life as a young mother on MTV’s Teen Mom franchise.
  • C. Rachel Solando
    Rachel Solando is a mysterious missing patient at a remote psychiatric hospital whose disappearance drives the psychological thriller plot of "Shutter Island."
  • D. Alyssa Cuban
    Alyssa Cuban is the daughter of American billionaire entrepreneur and Dallas Mavericks owner Mark Cuban and his wife Tiffany Stewart.
  • E. Lauren Vélez
    Lauren Vélez is an American actress best known for her role as Lieutenant Maria LaGuerta on the television series "Dexter."
  • 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_69e0b517e6748190850d6f6ddf323d69 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e7385c078881908a451be1a19a64c5 completed April 21, 2026, 8:42 a.m.
Created at: April 16, 2026, 4:05 p.m.