Triple
T7507389
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ecclefechan |
E177424
|
entity |
| Predicate | hasRoad |
P959
|
FINISHED |
| Object | A74(M) |
E247332
|
NE 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: A74(M) | Statement: [Ecclefechan, hasRoad, A74(M)]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: A74(M) Context triple: [Ecclefechan, hasRoad, A74(M)]
-
A.
M74
chosen
M74 is a major motorway in Scotland that connects Glasgow to the English border, forming part of the primary route between central Scotland and England.
-
B.
A7
A7 is a major European motorway designation used for key north–south and east–west highway routes in several countries.
-
C.
M-77
M-77 is a state highway in Michigan, United States, running north–south through the eastern Upper Peninsula.
-
D.
A470
A470 is a major trunk road in Wales that runs from Cardiff in the south to Llandudno in the north, linking many of the country’s key towns and regions.
-
E.
A73
A73 is a major German autobahn in Bavaria and Thuringia that links cities such as Lichtenfels with the broader national motorway network.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69c69f276b108190af2cc790b6554544 |
completed | March 27, 2026, 3:15 p.m. |
| NER | Named-entity recognition | batch_69c6f5b76a288190bb3608a5e3bfa212 |
completed | March 27, 2026, 9:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c83ca243288190bb253f4d91701407 |
completed | March 28, 2026, 8:40 p.m. |
Created at: March 27, 2026, 3:45 p.m.