Triple
T22236293
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Birmingham New Street – London Euston |
E549601
|
entity |
| Predicate | weekdayFrequency |
P90998
|
FINISHED |
| Object | multiple 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: multiple trains per hour | Statement: [Birmingham New Street – London Euston, weekdayFrequency, multiple trains per hour]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: weekdayFrequency Context triple: [Birmingham New Street – London Euston, weekdayFrequency, multiple trains per hour]
-
A.
weekdayServicePattern
Indicates a service pattern or schedule that specifically applies on weekdays rather than weekends or holidays.
-
B.
mentionsDayOfWeek
Indicates that something explicitly refers to or names a specific day of the week.
-
C.
typicalFrequencyWeekdayDaytime
chosen
Indicates the usual or most common frequency with which something occurs during daytime hours on weekdays.
-
D.
weekEndDay
Indicates that a given day falls on a weekend rather than a weekday.
-
E.
dayType
Indicates the classification or category of a given day based on its characteristics or role (e.g., weekday, weekend, holiday).
- 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_69e11e4102b881909cf47d3768e25c19 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f12bf7b1d8819091087dcfdb2e967c |
completed | April 28, 2026, 9:51 p.m. |
| PD | Predicate disambiguation | batch_69e71b5177d881908f90abde14ada7dc |
completed | April 21, 2026, 6:38 a.m. |
Created at: April 16, 2026, 8:38 p.m.