Triple
T20241406
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Belden Hill Road |
E498300
|
entity |
| Predicate | formsPartOfRouteThrough |
P6309
|
FINISHED |
| Object | the town of Wilton for Connecticut Route 53 |
—
|
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: the town of Wilton for Connecticut Route 53 | Statement: [Belden Hill Road, formsPartOfRouteThrough, the town of Wilton for Connecticut Route 53]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formsPartOfRouteThrough Context triple: [Belden Hill Road, formsPartOfRouteThrough, the town of Wilton for Connecticut Route 53]
-
A.
isPartOfRoute
chosen
Indicates that something (such as a segment, stop, or step) belongs to and is contained within a larger route.
-
B.
hasAlongRoute
Indicates that one entity lies on or is situated along the path, course, or route taken by another entity.
-
C.
roadNetworkPartOf
Indicates that one road network segment or component is a constituent part of a larger road network.
-
D.
locatedOnRouteTo
Indicates that one entity lies along the path or course taken when traveling from a starting point to a specified destination.
-
E.
followsRouteOf
Indicates that one entity travels along the same path or route that another entity takes or has taken.
- 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_69da6274c58c81909c646eabed6f4f30 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e6716eabf48190ae4e760f472114bd |
completed | April 20, 2026, 6:33 p.m. |
| PD | Predicate disambiguation | batch_69e55b1b23f88190bdcbe2f81dd226dd |
completed | April 19, 2026, 10:45 p.m. |
Created at: April 11, 2026, 11:40 p.m.