Triple
T354846
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cape Cod Canal Railroad Bridge |
E7520
|
entity |
| Predicate | clearanceBelowWhenRaised |
P12201
|
FINISHED |
| Object | 135 feet |
—
|
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: 135 feet | Statement: [Cape Cod Canal Railroad Bridge, clearanceBelowWhenRaised, 135 feet]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: clearanceBelowWhenRaised Context triple: [Cape Cod Canal Railroad Bridge, clearanceBelowWhenRaised, 135 feet]
-
A.
clearanceBelow
Indicates that one entity is positioned at a lower vertical clearance level than another, typically with less space between it and an underlying reference surface.
-
B.
hasClearanceBelow
Indicates that one entity’s clearance level is lower than another entity’s clearance level.
-
C.
heightRestriction
Indicates that there is a limit or constraint on how tall an entity is allowed or required to be in a given context.
-
D.
hasMezzanine
Indicates that one entity includes or is equipped with a mezzanine level in relation to another entity.
-
E.
canRaise
Indicates that one entity has the ability or authority to increase, elevate, or lift another entity (such as a value, object, or status).
- F. None of above. chosen
Provenance (4 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_69a2e7e696948190bebc966535995e45 |
completed | Feb. 28, 2026, 1:04 p.m. |
| NER | Named-entity recognition | batch_69a2eb8312f4819084dc222e665fded3 |
completed | Feb. 28, 2026, 1:20 p.m. |
| PD | Predicate disambiguation | batch_69a2e9589e7c8190b2d3af8f858c96af |
completed | Feb. 28, 2026, 1:10 p.m. |
| PDg | Predicate description generation | batch_69a2ea0a4c448190a8a179daa9b90645 |
completed | Feb. 28, 2026, 1:13 p.m. |
Created at: Feb. 28, 2026, 1:08 p.m.