Triple
T26815227
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fermont |
E672106
|
entity |
| Predicate | windbreakBuildingFunction |
P161593
|
FINISHED |
| Object | shields community from harsh Arctic winds |
—
|
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: shields community from harsh Arctic winds | Statement: [Fermont, windbreakBuildingFunction, shields community from harsh Arctic winds]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: windbreakBuildingFunction Context triple: [Fermont, windbreakBuildingFunction, shields community from harsh Arctic winds]
-
A.
windbreakBuildingFunction
chosen
Indicates that the building’s function is to act as a barrier that reduces wind speed or shields areas from wind.
-
B.
windbreakBuildingLength
Indicates the length dimension of a building used as a windbreak in relation to its wind-blocking function.
-
C.
functionInBuilding
Indicates that a specific function, role, or use is carried out within a particular building.
-
D.
seatBuildingFunction
Indicates that a building or structure serves a seating-related function, such as providing places for people to sit or be accommodated.
-
E.
roofFunction
Indicates the functional role or purpose that a roof serves in relation to the structure it covers.
- 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_69eeb3225a3c8190aaf6746efeded2f3 |
completed | April 27, 2026, 12:51 a.m. |
| NER | Named-entity recognition | batch_69f61fd623bc819091df736cf3419b99 |
completed | May 2, 2026, 4:01 p.m. |
| PD | Predicate disambiguation | batch_69f61b3d23f481908dfec27adace900a |
completed | May 2, 2026, 3:41 p.m. |
Created at: April 27, 2026, 4:31 a.m.