Triple
T2720920
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Elizabeth line |
E60076
|
entity |
| Predicate | serviceFrequencyCentralSectionPeak |
P20359
|
FINISHED |
| Object | up to 24 trains per hour |
—
|
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: up to 24 trains per hour | Statement: [Elizabeth line, serviceFrequencyCentralSectionPeak, up to 24 trains per hour]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: serviceFrequencyCentralSectionPeak Context triple: [Elizabeth line, serviceFrequencyCentralSectionPeak, up to 24 trains per hour]
-
A.
transitFrequencyApprox
chosen
Indicates an approximate rate or regularity with which a transit event or service occurs between entities.
-
B.
hasPeakHourService
Indicates that a service operates or is available during designated peak or high-demand hours.
-
C.
weekdayPeakDirectionService
Indicates that the service operates primarily during weekday peak travel periods in a specific direction.
-
D.
peakDayAttendance
Indicates the number of attendees present on the single highest-attendance day within a given period or event.
-
E.
rushHourServicePattern
Indicates that a service operates according to a specific pattern or schedule that applies only during rush-hour or peak travel times.
- 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_69ab4b746d248190958e052045c09255 |
completed | March 6, 2026, 9:47 p.m. |
| NER | Named-entity recognition | batch_69abdab1cb808190b0789c76bc9cb090 |
completed | March 7, 2026, 7:58 a.m. |
| PD | Predicate disambiguation | batch_69abd8240920819087a812d816a55edb |
completed | March 7, 2026, 7:47 a.m. |
Created at: March 6, 2026, 9:55 p.m.