Triple
T3216376
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thornton |
E67404
|
entity |
| Predicate | railJunctionOf |
P14465
|
FINISHED |
| Object | lines between Edinburgh and Dundee |
—
|
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: lines between Edinburgh and Dundee | Statement: [Thornton, railJunctionOf, lines between Edinburgh and Dundee]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: railJunctionOf Context triple: [Thornton, railJunctionOf, lines between Edinburgh and Dundee]
-
A.
railwayJunctionFor
Indicates that a location serves as a junction point where multiple railway lines or routes connect or intersect for a given railway network or service.
-
B.
transportationJunctionFor
Indicates a location that serves as a connecting point where multiple transportation routes or modes meet, intersect, or transfer.
-
C.
railTracks
Indicates that one entity consists of, includes, or is associated with rail tracks used for guiding trains or rail vehicles.
-
D.
junctionStation
chosen
Indicates that a station functions as a junction where multiple routes or lines intersect or connect.
-
E.
railroadTerminusFor
Indicates that one location serves as the end point or final station of a particular railroad line for another location.
- 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_69ad858b8adc8190ad989712c87a476b |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69adab096b588190b22e41a76263ae92 |
completed | March 8, 2026, 4:59 p.m. |
| PD | Predicate disambiguation | batch_69ad9e09b83881908801d79c3d9254f9 |
completed | March 8, 2026, 4:04 p.m. |
Created at: March 8, 2026, 3:07 p.m.