Triple
T20786309
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pontorson |
E511646
|
entity |
| Predicate | roadAccess |
P385
|
FINISHED |
| Object | D976 road |
—
|
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: D976 road | Statement: [Pontorson, roadAccess, D976 road]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: D976 road Context triple: [Pontorson, roadAccess, D976 road]
-
A.
D976 road
chosen
The D976 road is a regional route in France that serves as a key connector for the town of Mortain and surrounding areas.
-
B.
D996 road
The D996 road is a departmental route in southern France that serves as a key access road to the village of Meyrueis in the Cévennes region.
-
C.
D977 road
The D977 road is a departmental route in central France that serves as a key regional connector, including access to the town of Château-Chinon (Ville) in the Nièvre department.
-
D.
D97 road
The D97 road is a departmental route in the Île-de-France region of France that serves local traffic and connects small communes such as Précy-sur-Marne to the surrounding road network.
-
E.
D970 road
The D970 road is a departmental route in southern France that serves as a regional connector in and around the town of Tarascon.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b4cb83948190bd57bec21d78ed53 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c28c0d0c8190aa48e6fdfdaab750 |
completed | April 21, 2026, 12:19 a.m. |
Created at: April 16, 2026, 12:38 p.m.