Triple
T38618861
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Morfa Mawddach |
E936809
|
entity |
| Predicate | formerJunctionFor |
P113403
|
FINISHED |
| Object | Ruabon–Barmouth line |
—
|
NE NERFINISHED |
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: Ruabon–Barmouth line | Statement: [Morfa Mawddach, formerJunctionFor, Ruabon–Barmouth line]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formerJunctionFor Context triple: [Morfa Mawddach, formerJunctionFor, Ruabon–Barmouth line]
-
A.
wasJunctionFor
chosen
Indicates that one entity functioned as a junction or connecting point for another entity, typically serving as an intersection or hub through which the other entity passed or was routed.
-
B.
formerTerminusFor
Indicates that a location once served as the endpoint or final stop of a route, line, or service, but no longer holds that status.
-
C.
hasJunctionWith
Indicates that one entity meets or intersects with another at a shared junction point.
-
D.
formerStationNameFor
Indicates that one station name was previously used as the official name for another station.
-
E.
isJunction
Indicates that an entity functions as a junction point where multiple paths, lines, or connections meet or intersect.
- 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_69f76ed403208190b862dc795171353f |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a016336c58081909c58c5772e6fb488 |
completed | May 11, 2026, 5:03 a.m. |
| PD | Predicate disambiguation | batch_6a0160f25d8081909a6aaa375e9850b0 |
completed | May 11, 2026, 4:54 a.m. |
Created at: May 3, 2026, 4:32 p.m.