Triple
T12437596
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Neuilly-sur-Marne |
E297186
|
entity |
| Predicate | roadAccess |
P385
|
FINISHED |
| Object | A86 motorway |
E346811
|
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: A86 motorway | Statement: [Neuilly-sur-Marne, roadAccess, A86 motorway]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: A86 motorway Context triple: [Neuilly-sur-Marne, roadAccess, A86 motorway]
-
A.
A86 motorway
chosen
The A86 motorway is a major orbital highway forming part of the ring road system around Paris, France.
-
B.
A85 motorway
The A85 motorway is a French highway in central France that forms part of an east–west route linking cities such as Tours and Vierzon.
-
C.
A89 motorway
The A89 motorway is a major French highway running east–west across central France, linking cities such as Bordeaux, Clermont-Ferrand, and Lyon.
-
D.
A81 motorway
The A81 motorway is a major German autobahn running through the state of Baden-Württemberg, forming an important north–south transport corridor.
-
E.
A8 motorway
The A8 motorway is a major French highway in the Provence-Alpes-Côte d'Azur region that connects cities along the Mediterranean coast, including linking the Italian border area to Aix-en-Provence.
- 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_69d6ada166c48190b902972cd2408fa3 |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d94d8c8fd481909b35ac504127a1b6 |
completed | April 10, 2026, 7:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a007d960bd08190b8ac366273646865 |
completed | May 10, 2026, 12:44 p.m. |
Created at: April 8, 2026, 9:55 p.m.