Triple
T11163025
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Autoroute A4 |
E264086
|
entity |
| Predicate | roadNumber |
P1864
|
FINISHED |
| Object | A4 |
E237835
|
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: A4 | Statement: [Autoroute A4, roadNumber, A4]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: A4 Context triple: [Autoroute A4, roadNumber, A4]
-
A.
A4
A4 is a major European motorway designation used for important long-distance road routes in several countries.
-
B.
A4
chosen
A4 is a major French autoroute that connects Paris to the eastern regions of France and onward toward Germany.
-
C.
A4
A4 is a major west–east arterial road in London that forms part of the primary route between central London, Heathrow Airport, and the west of England.
-
D.
A4
A4 is a major Swiss motorway that connects the Zurich region with central and northern Switzerland, facilitating both national and international traffic.
-
E.
A5
A5 is a major Italian motorway connecting the city of Turin with the Aosta Valley and the Mont Blanc Tunnel at the French border.
- 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_69d6aa9ccddc8190868998c8b7beb060 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e8832fe88190a74d81f9ed547baa |
completed | April 9, 2026, 5:57 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e46375c61c8190939401f790cf1593 |
completed | April 19, 2026, 5:09 a.m. |
Created at: April 8, 2026, 9:29 p.m.