Triple

T34449331
Position Surface form Disambiguated ID Type / Status
Subject The Art of Massage E884315 entity
Predicate viewsMassageAs P102849 FINISHED
Object adjunct to medical treatment LITERAL 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: adjunct to medical treatment | Statement: [The Art of Massage, viewsMassageAs, adjunct to medical treatment]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: viewsMassageAs
Context triple: [The Art of Massage, viewsMassageAs, adjunct to medical treatment]
  • A. viewMaryAs
    Indicates that one entity perceives, regards, or interprets Mary in a particular way or role.
  • B. viewOnMass
    Indicates a relationship where something is visually oriented toward, overlooks, or has a direct view of a mass or large area.
  • C. viewsAs chosen
    Indicates that one entity perceives, interprets, or regards another entity in a particular way or role.
  • D. viewsGraceAs
    Indicates that one entity regards or perceives Grace in a particular way or role.
  • E. viewIs
    Indicates that one entity is a visual representation or perspective of another entity.
  • F. None of above.

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_69f349c607688190b553539d14901a35 completed April 30, 2026, 12:23 p.m.
NER Named-entity recognition batch_69f727bde8f88190ad746ca515134ca1 completed May 3, 2026, 10:47 a.m.
PD Predicate disambiguation batch_69f72739c30c81908642eef3feb3afcf completed May 3, 2026, 10:45 a.m.
Created at: May 1, 2026, 2 a.m.