Triple
T8102344
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Going-to-the-Sun Road |
E189144
|
entity |
| Predicate | typicallyOpenFrom |
P43960
|
FINISHED |
| Object | late June |
—
|
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: late June | Statement: [Going-to-the-Sun Road, typicallyOpenFrom, late June]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicallyOpenFrom Context triple: [Going-to-the-Sun Road, typicallyOpenFrom, late June]
-
A.
openingTime
chosen
Indicates the time at which a place, service, or event begins operating or becomes accessible.
-
B.
alsoOpenOn
Indicates that a place, service, or resource is open or available during an additional specified time or on an additional specified day beyond its primary opening period.
-
C.
openingHoursCharacteristic
Indicates a relationship that specifies particular attributes or features of an entity’s opening hours, such as patterns, exceptions, or special conditions.
-
D.
openedAt
Indicates that an entity began operating, became accessible, or was first made available at a specific time or date.
-
E.
operatorAtOpening
Indicates that an operator is present and on duty at the time of an opening event.
- 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_69ca82b886d88190a9cba0d5a4a27521 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb42bd91408190880293dfdce8bef7 |
completed | March 31, 2026, 3:42 a.m. |
| PD | Predicate disambiguation | batch_69cb04a14cd88190a79ed26cbeec1c33 |
completed | March 30, 2026, 11:17 p.m. |
Created at: March 30, 2026, 5:31 p.m.