Triple
T33617299
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Llanberis Lake Railway |
E861152
|
entity |
| Predicate | builtOnFormerTrackbedOf |
P14629
|
FINISHED |
| Object |
Padarn Railway
The Padarn Railway was a 19th-century narrow-gauge industrial railway in North Wales that primarily served the Dinorwic slate quarry, transporting slate to the port at Y Felinheli.
|
E2061053
|
NE FINISHED |
How this triple was built (3 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: Padarn Railway | Statement: [Llanberis Lake Railway, builtOnFormerTrackbedOf, Padarn Railway]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Padarn Railway Triple: [Llanberis Lake Railway, builtOnFormerTrackbedOf, Padarn Railway]
Generated description
The Padarn Railway was a 19th-century narrow-gauge industrial railway in North Wales that primarily served the Dinorwic slate quarry, transporting slate to the port at Y Felinheli.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: builtOnFormerTrackbedOf Context triple: [Llanberis Lake Railway, builtOnFormerTrackbedOf, Padarn Railway]
-
A.
locatedOnFormerRailway
Indicates that something is situated on the route or site of a railway line that is no longer in operation.
-
B.
formerTransportInfrastructure
Indicates that an entity was once used as transport infrastructure but no longer serves that function.
-
C.
followsFormerRailroad
chosen
Indicates that something is aligned with or traces the route of a former railroad line.
-
D.
rebuiltOnSiteOf
Indicates that a structure was reconstructed or newly built on the same physical location where an earlier structure once stood.
-
E.
railTracks
Indicates that one entity consists of, includes, or is associated with rail tracks used for guiding trains or rail vehicles.
- F. None of above.
Provenance (6 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_69f34980fabc81909819228729a9ca84 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f6f818d0588190b62399a5c5e9fa21 |
completed | May 3, 2026, 7:24 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a36271342ec81908fe9b5625ee7fda9 |
completed | June 20, 2026, 5:37 a.m. |
| NEDg | Description generation | batch_6a36287379bc819093531d0ca6f2e2b1 |
completed | June 20, 2026, 5:43 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a36290ab68081908c16a32eac142a8d |
completed | June 20, 2026, 5:45 a.m. |
| PD | Predicate disambiguation | batch_69f6f6632dfc8190af85e258c8519207 |
completed | May 3, 2026, 7:16 a.m. |
Created at: May 1, 2026, 1:41 a.m.