Triple
T25341638
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mentone railway station |
E635428
|
entity |
| Predicate | gradeSeparationCompleted |
P96763
|
FINISHED |
| Object | 2021 |
—
|
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: 2021 | Statement: [Mentone railway station, gradeSeparationCompleted, 2021]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: gradeSeparationCompleted Context triple: [Mentone railway station, gradeSeparationCompleted, 2021]
-
A.
gradeSeparationProject
Indicates a project whose purpose is to separate different transportation routes or levels (such as roads and railways) so they no longer intersect at the same grade.
-
B.
gradeSeparated
chosen
Indicates that two intersecting transportation routes are physically separated by different elevation levels so they do not cross at the same grade.
-
C.
typeOfSeparation
Indicates the specific manner or category of separation that exists or occurred between entities.
-
D.
gradeWithin
Indicates that one value’s grade or level falls within a specified range or interval relative to another.
-
E.
providesSeparationFor
Indicates that one entity serves to divide, isolate, or keep another entity apart from something else.
- 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_69e75a99bd6481909476115b35b9a8e4 |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f498b818008190a4240a7a2cbeedfd |
completed | May 1, 2026, 12:12 p.m. |
| PD | Predicate disambiguation | batch_69f4806d93dc8190b9dff4c63186faff |
completed | May 1, 2026, 10:29 a.m. |
Created at: April 21, 2026, 1:32 p.m.