Triple
T4385230
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | UP Express |
E99224
|
entity |
| Predicate | headwayPeak |
P22511
|
FINISHED |
| Object | 15 minutes |
—
|
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: 15 minutes | Statement: [UP Express, headwayPeak, 15 minutes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: headwayPeak Context triple: [UP Express, headwayPeak, 15 minutes]
-
A.
headway
chosen
Indicates the temporal or spatial separation maintained between moving entities, such as vehicles or trains, as they travel along the same route.
-
B.
isTransPennineRoute
Indicates that something is a route crossing the Pennines, typically connecting locations on opposite sides of the Pennine mountain range.
-
C.
publicTransportAuthority
Indicates that one entity serves as the governing or managing authority responsible for overseeing public transportation services related to another entity.
-
D.
hasBakerlooPlatformsBetween
Indicates that there are Bakerloo line platforms located between two specified points or stations.
-
E.
hasPiccadillyPlatformsBetween
Indicates that one station has Piccadilly line platforms located between it and another station along the route.
- 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_69b3454f739481909ff6c28331f0c0b9 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b35264e44c81908dd0e0a81f1353bb |
completed | March 12, 2026, 11:55 p.m. |
| PD | Predicate disambiguation | batch_69b34f572efc8190bad1e5078cbcb75a |
completed | March 12, 2026, 11:42 p.m. |
Created at: March 12, 2026, 11:19 p.m.