Triple
T13248866
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New Beckenham railway station |
E315474
|
entity |
| Predicate | hasHelpPointOnPlatforms |
P3793
|
FINISHED |
| Object | yes |
—
|
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: yes | Statement: [New Beckenham railway station, hasHelpPointOnPlatforms, yes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasHelpPointOnPlatforms Context triple: [New Beckenham railway station, hasHelpPointOnPlatforms, yes]
-
A.
hasHelpPoint
chosen
Indicates that one entity provides or contains a designated help or assistance point for another entity.
-
B.
hasAtGradePlatforms
Indicates that the subject has platforms located at the same level as the surrounding ground or track (i.e., not elevated or underground).
-
C.
hasPrimaryPlatform
Indicates that one entity is designated as the main or principal platform associated with another entity.
-
D.
hasRegionalPlatforms
Indicates that an entity operates or is associated with specific platforms that are organized or deployed at a regional level.
-
E.
supportedPlatform
Indicates that one entity (such as a system, application, or service) is compatible with and can operate on a particular platform.
- 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_69d806b1072881909e46bd212259c5f0 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d98d9e7ea881908abc4b3a54896692 |
completed | April 10, 2026, 11:54 p.m. |
| PD | Predicate disambiguation | batch_69d98bcca7d88190a3e68e99ed3a29e6 |
completed | April 10, 2026, 11:46 p.m. |
Created at: April 9, 2026, 9:24 p.m.