Triple
T26038203
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | A38(M) Aston Expressway |
E647611
|
entity |
| Predicate | hasJunctionName |
P160318
|
FINISHED |
| Object | Gravelly Hill Interchange |
—
|
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: Gravelly Hill Interchange | Statement: [A38(M) Aston Expressway, hasJunctionName, Gravelly Hill Interchange]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasJunctionName Context triple: [A38(M) Aston Expressway, hasJunctionName, Gravelly Hill Interchange]
-
A.
hasJunctionType
Indicates the specific kind or classification of a junction associated with an entity.
-
B.
hasJunctionIn
Indicates that one entity contains or includes a junction located within the spatial or structural extent of another entity.
-
C.
hasJunctionWith
Indicates that one entity meets or intersects with another at a shared junction point.
-
D.
hasJunctionFunction
Indicates that one entity serves as a junction or connecting function for another entity within a system or structure.
-
E.
hasJunctionNumber
Indicates that a road, route, or similar pathway is assigned a specific junction or exit number.
- F. None of above. chosen
Provenance (4 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_69e77e8c88f08190858c4c81bd2e1b9a |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f6061fd954819082000e723287e423 |
completed | May 2, 2026, 2:11 p.m. |
| PD | Predicate disambiguation | batch_69f5f7fba5248190945acf1561280799 |
completed | May 2, 2026, 1:11 p.m. |
| PDg | Predicate description generation | batch_69f600be0de88190989611e952b03117 |
completed | May 2, 2026, 1:48 p.m. |
Created at: April 22, 2026, 9:08 a.m.