Triple
T9662945
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Birmingham New Street to Liverpool Lime Street |
E233630
|
entity |
| Predicate | typicalFrequencyOffPeak |
P24204
|
FINISHED |
| Object | at least hourly |
—
|
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: at least hourly | Statement: [Birmingham New Street to Liverpool Lime Street, typicalFrequencyOffPeak, at least hourly]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalFrequencyOffPeak Context triple: [Birmingham New Street to Liverpool Lime Street, typicalFrequencyOffPeak, at least hourly]
-
A.
typicalOffPeakServiceTo
Indicates the usual or standard off-peak (non-peak time) service pattern that operates to a given destination.
-
B.
typicalPeriod
Indicates the usual or characteristic time interval or duration associated with an event, process, or state.
-
C.
offPeakServicePattern
chosen
Indicates the service pattern or schedule that applies during off-peak (non-rush-hour) times.
-
D.
peakHours
Indicates that an action, event, or condition occurs during the busiest or most heavily trafficked time period.
-
E.
typicalTimes
Indicates the usual or characteristic times at which an event, activity, or condition typically occurs.
- 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_69ca848d3b6c8190ae98ea554dea58df |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd9c0cde048190b5a8e1548825d4d9 |
completed | April 1, 2026, 10:28 p.m. |
| PD | Predicate disambiguation | batch_69ccd5b3239c8190b3ae3b9bd121e4bd |
completed | April 1, 2026, 8:22 a.m. |
Created at: March 30, 2026, 8:14 p.m.