Triple
T1319228
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Caledonian Sleeper |
E28176
|
entity |
| Predicate | operatingPattern |
P26963
|
FINISHED |
| Object | overnight |
—
|
LITERAL 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: overnight | Statement: [Caledonian Sleeper, operatingPattern, overnight]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: operatingPattern Context triple: [Caledonian Sleeper, operatingPattern, overnight]
-
A.
operatingModel
Indicates how an organization structures and manages its processes, resources, and governance to deliver its products or services.
-
B.
operatesBy
Indicates that an entity performs its function, action, or process through the use or application of another entity (e.g., a method, mechanism, or principle).
-
C.
operatesOver
Indicates that one entity performs actions or exerts functional control across, upon, or throughout another entity or domain.
-
D.
acquisitionPattern
Indicates the characteristic way in which one entity acquires or obtains another entity or resource, such as the method, frequency, or structure of the acquisition.
-
E.
kitPattern
Indicates the design or visual pattern featured on a team's kit or uniform.
- F. None of above. chosen
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_69a498532c3481909223b74af2e578df |
completed | March 1, 2026, 7:49 p.m. |
| NER | Named-entity recognition | batch_69a4c1780be8819083a9365b8a49305d |
completed | March 1, 2026, 10:45 p.m. |
| PD | Predicate disambiguation | batch_69a4beebcb348190964bd7215811942c |
completed | March 1, 2026, 10:34 p.m. |
| PDg | Predicate description generation | batch_69a4bfc2134c81909cbaaa151d96e9a8 |
completed | March 1, 2026, 10:37 p.m. |
Created at: March 1, 2026, 7:55 p.m.