Triple
T32748896
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Leeds to Doncaster line |
E837437
|
entity |
| Predicate | junction |
P71091
|
FINISHED |
| Object | Colton Junction |
—
|
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: Colton Junction | Statement: [Leeds to Doncaster line, junction, Colton Junction]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: junction Context triple: [Leeds to Doncaster line, junction, Colton Junction]
-
A.
junctionOf
chosen
Indicates that one or more entities meet or intersect at a common point, forming a junction between them.
-
B.
junctionType
Indicates the specific kind or configuration of a junction that relates connected elements or paths.
-
C.
junctionFunction
Indicates a functional relationship where one entity serves as a junction or connection point integrating or routing flows, signals, or interactions between multiple other entities.
-
D.
union
Indicates that two or more sets are combined into a single set containing all elements that belong to at least one of them.
-
E.
junctionNumber
Indicates the identifying number assigned to a specific junction or intersection within a network or system.
- 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_69f34937f97c8190b7f84bea045df3ae |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6cd126fcc8190aa1f1f146e45ec0c |
completed | May 3, 2026, 4:20 a.m. |
| PD | Predicate disambiguation | batch_69f6cc1470808190b70cdfd7a6395670 |
completed | May 3, 2026, 4:16 a.m. |
Created at: May 1, 2026, 1:12 a.m.