Triple
T34800790
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | London–Cardiff |
E1003212
|
entity |
| Predicate | hasPrimaryRailTerminusInCardiff |
P204110
|
FINISHED |
| Object | Cardiff Central railway station |
E58613
|
NE 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: Cardiff Central railway station | Statement: [London–Cardiff, hasPrimaryRailTerminusInCardiff, Cardiff Central railway station]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPrimaryRailTerminusInCardiff Context triple: [London–Cardiff, hasPrimaryRailTerminusInCardiff, Cardiff Central railway station]
-
A.
hasNationalRailService
Indicates that a place or facility is served by a country's national rail transportation network.
-
B.
hasNationalRailCategory
Indicates that an entity is assigned a specific classification or category within a national rail system.
-
C.
hasNationalRailPlatforms
Indicates that an entity possesses one or more platforms used by the national rail network for train services.
-
D.
hasRailTerminusInManchester
Indicates that something has its rail terminus (end point of a railway line or service) located in Manchester.
-
E.
servesAsRailheadFor
Indicates that one location functions as the primary loading, unloading, or distribution point on a railway network for another area or operation.
- F. None of above. chosen
Provenance (5 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_69f76db543808190b188c6c86a91491b |
completed | May 3, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_6a032616547c8190bc877202e43403eb |
completed | May 12, 2026, 1:07 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a376fabe43c8190803d59ef868042d0 |
completed | June 21, 2026, 4:59 a.m. |
| PD | Predicate disambiguation | batch_6a0325246abc819088e16a7fbadf40c5 |
completed | May 12, 2026, 1:03 p.m. |
| PDg | Predicate description generation | batch_6a032615ac7c81908c917e1be93c1189 |
completed | May 12, 2026, 1:07 p.m. |
Created at: May 3, 2026, 3:59 p.m.