Triple
T11928252
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Le Roy, Minnesota |
E283839
|
entity |
| Predicate | recreationNearby |
P68166
|
FINISHED |
| Object | hiking at Lake Louise State Park |
—
|
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: hiking at Lake Louise State Park | Statement: [Le Roy, Minnesota, recreationNearby, hiking at Lake Louise State Park]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: recreationNearby Context triple: [Le Roy, Minnesota, recreationNearby, hiking at Lake Louise State Park]
-
A.
operatorOfRecreationArea
Indicates that an entity is responsible for managing, running, or overseeing the operations of a recreation area.
-
B.
hasRecreationalUseNearby
chosen
Indicates that there is at least one location or facility for recreational activities situated close to the referenced entity.
-
C.
hasRecreationalOrganization
Indicates that an entity is associated with, or hosts, a recreational organization such as a club, team, or leisure group.
-
D.
nearbyCampground
Indicates that one location has a campground situated close to it in geographic proximity.
-
E.
recreationAccessPoint
Indicates a location or facility that serves as an entry or starting point for engaging in recreational activities.
- 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_69d6ab2ce9c48190b5d39511b524f666 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d903024afc8190a97aa3263dc7d017 |
completed | April 10, 2026, 2:02 p.m. |
| PD | Predicate disambiguation | batch_69d8bb3af0188190bfb22be5c97b3349 |
completed | April 10, 2026, 8:56 a.m. |
Created at: April 8, 2026, 9:45 p.m.