Triple
T35423719
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ivybridge railway station |
E1023862
|
entity |
| Predicate | isOnMainRouteBetween |
P179331
|
FINISHED |
| Object | Exeter |
—
|
NE NERFINISHED |
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: Exeter | Statement: [Ivybridge railway station, isOnMainRouteBetween, Exeter]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isOnMainRouteBetween Context triple: [Ivybridge railway station, isOnMainRouteBetween, Exeter]
-
A.
includesRouteBetween
Indicates that one entity (such as a service, plan, or network) contains or provides a specific route connecting two locations or points.
-
B.
onMajorRouteBetween
chosen
Indicates that one location lies along a primary or major route connecting two other locations.
-
C.
isMajorRouteThrough
Indicates that a route serves as a primary or significant pathway passing through a specified area or location.
-
D.
isRouteOn
Indicates that one route is located on, follows along, or is aligned with another specified path or infrastructure.
-
E.
isScenicConnectorBetween
Indicates that something serves as a visually appealing route or link connecting two locations or entities.
- 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_69f76df6704081909900c60be10d5849 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7958ef49081909e4a8bfe3ef0d657 |
completed | May 3, 2026, 6:35 p.m. |
| PD | Predicate disambiguation | batch_69f7910770108190bdd39ddb5d304f54 |
completed | May 3, 2026, 6:16 p.m. |
Created at: May 3, 2026, 4:03 p.m.