Triple
T10552200
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brockville Railway Tunnel |
E248978
|
entity |
| Predicate | hasVentilationFeature |
P31158
|
FINISHED |
| Object | vertical shafts |
—
|
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: vertical shafts | Statement: [Brockville Railway Tunnel, hasVentilationFeature, vertical shafts]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasVentilationFeature Context triple: [Brockville Railway Tunnel, hasVentilationFeature, vertical shafts]
-
A.
ventilationFeature
Indicates that one entity has a structural or functional role related to providing, enabling, or affecting ventilation for another entity.
-
B.
hasVentilationShafts
chosen
Indicates that one entity is equipped with or contains ventilation shafts that provide airflow or air passage.
-
C.
hasFlankVents
Indicates that an entity possesses vents located on its sides or flanks.
-
D.
hasAirConditioning
Indicates that an entity is equipped with or provides air conditioning.
-
E.
hasVentilationBuildings
Indicates that certain buildings are designated to provide ventilation for another structure, area, or system.
- 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.