Triple
T3579763
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bagshot railway station |
E75770
|
entity |
| Predicate | typicalOffPeakServiceToAscot |
P24204
|
FINISHED |
| Object | 2 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: 2 trains per hour | Statement: [Bagshot railway station, typicalOffPeakServiceToAscot, 2 trains per hour]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalOffPeakServiceToAscot Context triple: [Bagshot railway station, typicalOffPeakServiceToAscot, 2 trains per hour]
-
A.
offPeakServicePattern
chosen
Indicates the service pattern or schedule that applies during off-peak (non-rush-hour) times.
-
B.
rushHourServicePattern
Indicates that a service operates according to a specific pattern or schedule that applies only during rush-hour or peak travel times.
-
C.
typicalTimes
Indicates the usual or characteristic times at which an event, activity, or condition typically occurs.
-
D.
peakServiceOnly
Indicates that the service operates only during peak periods and is not available at off-peak times.
-
E.
servesCentralLondon
Indicates that something provides service or access specifically to the Central London area.
- 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_69ad85d5e3008190bdfe0bacdd1f5a1b |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc0ffecdc8190bf01c8ba90e3733e |
completed | March 8, 2026, 6:33 p.m. |
| PD | Predicate disambiguation | batch_69adb83810c481909c645c08b978edc1 |
completed | March 8, 2026, 5:56 p.m. |
Created at: March 8, 2026, 3:21 p.m.