Triple

T10031047
Position Surface form Disambiguated ID Type / Status
Subject Sky Tonia Ferreira E204851 entity
Predicate notableSingle P3283 FINISHED
Object Obsession E205745 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: Obsession | Statement: [Sky Tonia Ferreira, notableSingle, Obsession]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Obsession
Context triple: [Sky Tonia Ferreira, notableSingle, Obsession]
  • A. Obsession
    Obsession is a novel by American crime writer Lionel White, known for its hardboiled suspense and for inspiring Jean-Luc Godard’s film "Pierrot le Fou."
  • B. Obsession chosen
    "Obsession" is a synth-pop single by American singer Sky Ferreira that helped introduce her dark, edgy pop aesthetic to a wider audience.
  • C. Obsession
    Obsession is a 1976 psychological thriller film directed by Brian De Palma, known for its Hitchcockian style, themes of guilt and identity, and Bernard Herrmann’s haunting score.
  • D. Obsessed
    Obsessed is a social media account or online persona that is followed by the user Cinco.
  • E. Obsessed
    Obsessed is a work by creator Ken Seng, recognized as one of his notable contributions to his field.
  • 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_69ca834d77188190ad645e33e8ca3200 completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cdcde7ec088190845656cc2529c771 completed April 2, 2026, 2:01 a.m.
NED1 Entity disambiguation (via context triple) batch_69d2823e63488190bef7633b1a755df8 completed April 5, 2026, 3:39 p.m.
Created at: March 30, 2026, 8:54 p.m.