Triple
T10552186
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brockville Railway Tunnel |
E248978
|
entity |
| Predicate | reopeningDateAsAttraction |
P10067
|
FINISHED |
| Object | 2017 |
—
|
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: 2017 | Statement: [Brockville Railway Tunnel, reopeningDateAsAttraction, 2017]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reopeningDateAsAttraction Context triple: [Brockville Railway Tunnel, reopeningDateAsAttraction, 2017]
-
A.
reopeningDate
chosen
Indicates the date on which something that was previously closed is opened again for use or access.
-
B.
originalAttractionOpeningDate
Indicates the date on which the attraction first opened to the public in its original form or location.
-
C.
openingDayAttractionOf
Indicates that one entity serves as the main or featured attraction for another entity specifically on its opening day.
-
D.
partialReopeningDate
Indicates the date on which an entity is reopened in a limited or partial capacity, rather than fully resuming normal operation.
-
E.
openingDateAsPark
Indicates the date on which a place or area was first officially opened and began operating as a park.
- 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_69d381c733c08190ab1dd6239f5f34ae |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d52710869c81909b6db1a190825bad |
completed | April 7, 2026, 3:47 p.m. |
| PD | Predicate disambiguation | batch_69d518fa0b4081909bffc936d78bd77b |
completed | April 7, 2026, 2:47 p.m. |
Created at: April 6, 2026, 12:34 p.m.