Triple
T15009647
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | London Waterloo to Bournemouth |
E377800
|
entity |
| Predicate | hasDailyFrequency |
P27954
|
FINISHED |
| Object | multiple trains per hour at peak times |
—
|
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 at peak times | Statement: [London Waterloo to Bournemouth, hasDailyFrequency, multiple trains per hour at peak times]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDailyFrequency Context triple: [London Waterloo to Bournemouth, hasDailyFrequency, multiple trains per hour at peak times]
-
A.
hasDailyUse
Indicates that something is used or occurs on a daily, regular basis.
-
B.
hasDailyMarket
Indicates that an entity regularly hosts or participates in a market that operates on a daily basis.
-
C.
hasDailyEvent
Indicates that an entity is associated with an event that occurs every day.
-
D.
hasDailyService
chosen
Indicates that a service or operation occurs every day on a regular, scheduled basis.
-
E.
hasDailyTraffic
Indicates that an entity experiences or is associated with a certain amount or pattern of traffic on a daily basis.
- 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_69d85cd3a3c881908c71fc424d459c17 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded734943481908dad4ceed4fe850c |
completed | April 15, 2026, 12:09 a.m. |
| PD | Predicate disambiguation | batch_69de9a6531a88190acde65199a477350 |
completed | April 14, 2026, 7:49 p.m. |
Created at: April 10, 2026, 2:55 a.m.