Triple
T3857556
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Manitoba Museum |
E90054
|
entity |
| Predicate | hasExhibitStyle |
P27951
|
FINISHED |
| Object | immersive galleries |
—
|
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: immersive galleries | Statement: [Manitoba Museum, hasExhibitStyle, immersive galleries]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasExhibitStyle Context triple: [Manitoba Museum, hasExhibitStyle, immersive galleries]
-
A.
exhibitStyle
chosen
Indicates that an entity displays, demonstrates, or embodies a particular style or manner of expression.
-
B.
hasExhibitFormat
Indicates the specific format or medium in which an exhibit is presented or made available.
-
C.
hasExhibits
Indicates that an entity (such as a museum, gallery, or event) displays or presents certain items, artworks, or objects as part of its collection or show.
-
D.
hasExhibitElement
Indicates that something (such as an exhibit or display) includes or is composed of a particular element or component.
-
E.
hasExhibitionModel
Indicates that one entity serves as the exhibition or display model associated with 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_69aed95b3c088190a8f85d19e6070599 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aeec09312c81908ffd7441c83730c8 |
completed | March 9, 2026, 3:49 p.m. |
| PD | Predicate disambiguation | batch_69aee752c8a48190a670f73ed0bf1e61 |
completed | March 9, 2026, 3:29 p.m. |
Created at: March 9, 2026, 3:19 p.m.