Triple
T37203021
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lumo (Class 803 variant) |
E922091
|
entity |
| Predicate | primaryRouteCorridor |
P46518
|
FINISHED |
| Object | London–Edinburgh |
E157902
|
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: London–Edinburgh | Statement: [Lumo (Class 803 variant), primaryRouteCorridor, London–Edinburgh]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryRouteCorridor Context triple: [Lumo (Class 803 variant), primaryRouteCorridor, London–Edinburgh]
-
A.
primaryRouteThrough
Indicates that one location or path serves as the main or most significant route passing through another location or area.
-
B.
primaryCorridorServed
chosen
Indicates that a corridor is the main route or pathway served by a given service, facility, or entity.
-
C.
primaryRouteType
Indicates the main category or kind of route associated with an entity, such as its primary mode, path, or routing classification.
-
D.
primaryRouteOf
Indicates that one route is the main or most important pathway used for reaching or connecting to a particular destination or entity.
-
E.
primaryRoute
Indicates that one route is designated as the main or preferred path among possible alternatives between locations.
- F. None of above.
Provenance (4 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_69f76ea4849481909b4a3073efb0114c |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a037c8efcd4819088c2aeead65d93df |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a40361d77108190b780b0486ccf80d3 |
completed | June 27, 2026, 8:44 p.m. |
| PD | Predicate disambiguation | batch_6a037a11efc08190bb7cacc1325b4dc6 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:15 p.m.