Triple
T15880081
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mancunian Way |
E385052
|
entity |
| Predicate | connects |
P390
|
FINISHED |
| Object | A57 |
E433904
|
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: A57 | Statement: [Mancunian Way, connects, A57]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: A57 Context triple: [Mancunian Way, connects, A57]
-
A.
A57
chosen
The A57 is a major road in the United Kingdom that connects several towns and cities across northern England, providing an important east–west transport route.
-
B.
A55
A55 is a major Australian highway route designation used for sections of the Castlereagh Highway in New South Wales.
-
C.
A55
The A55 is a major road in North Wales that forms part of the key route along the north coast, linking towns such as Hawarden to the wider regional and national road network.
-
D.
A56
The A56 is a major road in North West England that runs between Chester and Broughton, passing through key urban areas including Manchester.
-
E.
A505
A505 is a major road in England that serves as an important route connecting the town of Dunstable with other parts of the region.
- 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_69d86da4e86481909f1325fdc971b5ec |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e15600863c8190a2dbfd6d7ff495d7 |
completed | April 16, 2026, 9:34 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffa9529ac48190993d1af234faea3b |
completed | May 9, 2026, 9:38 p.m. |
Created at: April 10, 2026, 4:51 a.m.