Triple
T30612929
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Newbury Park tube station |
E779230
|
entity |
| Predicate | laterRailwayGroup |
P55892
|
FINISHED |
| Object | London and North Eastern Railway |
—
|
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: London and North Eastern Railway | Statement: [Newbury Park tube station, laterRailwayGroup, London and North Eastern Railway]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: laterRailwayGroup Context triple: [Newbury Park tube station, laterRailwayGroup, London and North Eastern Railway]
-
A.
laterRailwayCompany
chosen
Indicates that one railway company is the successor or later incarnation of another railway company.
-
B.
railwayCompanyGroup
Indicates that one entity is a group or consortium that includes or controls the other entity as a railway company.
-
C.
formerRailOperator
Indicates that an entity previously operated a rail service or railway system but no longer does so.
-
D.
railwayCompany
Indicates that one entity is a railway company that owns, operates, or manages railway services or infrastructure in relation to another entity.
-
E.
railwayOpenedBy
Indicates that a railway was initiated, constructed, or put into operation by a specific agent or organization.
- 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_69f224a3307081909a6dca8ca75dbf48 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69feff70fbec8190b1ff5f943f29613e |
completed | May 9, 2026, 9:33 a.m. |
| PD | Predicate disambiguation | batch_69fefbcd5b7881909cfe52b32f8a4301 |
completed | May 9, 2026, 9:18 a.m. |
Created at: April 29, 2026, 8:26 p.m.