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.