Triple
T426017
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nathan Phillips Square |
E9608
|
entity |
| Predicate | winterFeature |
P10789
|
FINISHED |
| Object | outdoor skating rink |
—
|
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: outdoor skating rink | Statement: [Nathan Phillips Square, winterFeature, outdoor skating rink]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: winterFeature Context triple: [Nathan Phillips Square, winterFeature, outdoor skating rink]
-
A.
winterCharacteristic
chosen
Indicates a characteristic, feature, or quality that is specifically associated with or typical of winter.
-
B.
snowCover
Indicates that one entity is covered by or blanketed with snow.
-
C.
snowRemovalBy
Indicates that one entity performs or is responsible for removing snow from another entity or location.
-
D.
summerHomeOf
Indicates that a location serves as a seasonal or vacation residence for a person or group, specifically used during the summer.
-
E.
requiresFrostFreeSeason
Indicates that the subject depends on a period without frost to grow, develop, or function properly.
- 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_69a2e801e1d48190b505d1dd336b52ac |
completed | Feb. 28, 2026, 1:05 p.m. |
| NER | Named-entity recognition | batch_69a2eed691c4819092b7e57306114bbc |
completed | Feb. 28, 2026, 1:34 p.m. |
| PD | Predicate disambiguation | batch_69a2edd6736c81909a6ca549f77b4345 |
completed | Feb. 28, 2026, 1:29 p.m. |
Created at: Feb. 28, 2026, 1:11 p.m.