Triple
T34732060
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eaton’s 9th Floor Restaurant in Winnipeg |
E1001237
|
entity |
| Predicate | floorLevelType |
P181808
|
FINISHED |
| Object | upper-floor restaurant |
—
|
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: upper-floor restaurant | Statement: [Eaton’s 9th Floor Restaurant in Winnipeg, floorLevelType, upper-floor restaurant]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: floorLevelType Context triple: [Eaton’s 9th Floor Restaurant in Winnipeg, floorLevelType, upper-floor restaurant]
-
A.
doorFloorLevel
Indicates that a door is located at or associated with a specific floor level within a building or structure.
-
B.
floorType
Indicates the type or material classification of a floor associated with an entity.
-
C.
floorHeight
Indicates the vertical elevation or level at which a particular floor is positioned within a structure.
-
D.
floorAbove
Indicates that one floor is located directly above another floor in a vertical arrangement.
-
E.
floorBelow
Indicates that one entity is located on the floor directly beneath another entity within the same structure.
- F. None of above. chosen
Provenance (4 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_69f76daf739881909ed3554f98a2b433 |
completed | May 3, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69f7824dc3f0819092a5102895b4a478 |
completed | May 3, 2026, 5:13 p.m. |
| PD | Predicate disambiguation | batch_69f780fc5ed88190b7200ee5a29940af |
completed | May 3, 2026, 5:08 p.m. |
| PDg | Predicate description generation | batch_69f7817c79e081908e685c48165e086b |
completed | May 3, 2026, 5:10 p.m. |
Created at: May 3, 2026, 3:59 p.m.