Triple
T15448363
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Quai de la Gare |
E370081
|
entity |
| Predicate | platformCanopy |
P118828
|
FINISHED |
| Object | metal and glass canopy |
—
|
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: metal and glass canopy | Statement: [Quai de la Gare, platformCanopy, metal and glass canopy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: platformCanopy Context triple: [Quai de la Gare, platformCanopy, metal and glass canopy]
-
A.
platformMate
Indicates that two entities are located on the same platform or share the same platform context at a given time.
-
B.
platformHeight
Indicates the vertical distance or elevation of a platform relative to a defined reference level.
-
C.
platformShowcased
Indicates that a platform is prominently presented or highlighted, typically to draw attention to its features, capabilities, or offerings.
-
D.
platformPlanned
Indicates that a platform is intended or scheduled to be created, implemented, or made available in the future.
-
E.
platformInterface
Indicates that one entity serves as an interface or interaction layer through which another entity accesses or communicates with a broader platform or system.
- 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_69d85a19180081909925012fbf4e62a3 |
completed | April 10, 2026, 2:02 a.m. |
| NER | Named-entity recognition | batch_69e03ef9334c81908541e231b43eb012 |
completed | April 16, 2026, 1:44 a.m. |
| PD | Predicate disambiguation | batch_69ded28276f481908c2038bb301e57cf |
completed | April 14, 2026, 11:49 p.m. |
| PDg | Predicate description generation | batch_69ded57005608190886cd01f640dfedb |
completed | April 15, 2026, 12:01 a.m. |
Created at: April 10, 2026, 3:21 a.m.