Triple
T6951251
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cadoxton railway station |
E160928
|
entity |
| Predicate | serviceFrequencySunday |
P55256
|
FINISHED |
| Object | reduced frequency |
—
|
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: reduced frequency | Statement: [Cadoxton railway station, serviceFrequencySunday, reduced frequency]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: serviceFrequencySunday Context triple: [Cadoxton railway station, serviceFrequencySunday, reduced frequency]
-
A.
weekendService
Indicates that a service, operation, or activity is provided or occurs specifically on weekends.
-
B.
serviceFrequencyType
chosen
Indicates how often a service occurs or is scheduled within a given time period.
-
C.
observedIfOnSunday
Indicates that the observation or event occurs or is recorded only when the relevant time falls on a Sunday.
-
D.
serviceFrequencyContext
Indicates the contextual conditions or circumstances under which a service’s frequency is defined, applied, or interpreted.
-
E.
sundayLawDate
Indicates the date on which a specific Sunday law is enacted, comes into effect, or is scheduled to be observed.
- 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_69c68850419081909fb426b8f5a304c7 |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6dacca12481908942ba793a104cc3 |
completed | March 27, 2026, 7:30 p.m. |
| PD | Predicate disambiguation | batch_69c6d7bf0a7c8190b5ed4aca22ba9b97 |
completed | March 27, 2026, 7:17 p.m. |
Created at: March 27, 2026, 2:29 p.m.