Triple
T14795572
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brynglas |
E347766
|
entity |
| Predicate | hasPassingLoopDirection |
P36771
|
FINISHED |
| Object | allows trains to cross in both directions |
—
|
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: allows trains to cross in both directions | Statement: [Brynglas, hasPassingLoopDirection, allows trains to cross in both directions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPassingLoopDirection Context triple: [Brynglas, hasPassingLoopDirection, allows trains to cross in both directions]
-
A.
hasLoopDirectionOptions
chosen
Indicates that an entity provides or supports multiple possible directions in which a loop can operate or be executed.
-
B.
hasPassingLoopAt
Indicates that a railway line or track segment includes a passing loop located at a specified place or point.
-
C.
hasLoopMode
Indicates that an entity operates or is configured in a mode where its behavior or process repeats in a loop.
-
D.
hasLoopRole
Indicates that an entity participates in a loop structure with a specific functional role within that loop.
-
E.
hasVerticalLoops
Indicates that one entity features or includes vertical loop structures in its form, design, or configuration.
- 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_69d822ea8b7c819097dfadf3d45545e6 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69decd5fdd548190a2ee5e668c2b20b4 |
completed | April 14, 2026, 11:27 p.m. |
| PD | Predicate disambiguation | batch_69de8c090d1081909b5a9bf437499d6c |
completed | April 14, 2026, 6:48 p.m. |
Created at: April 10, 2026, 1:31 a.m.