Triple
T19007117
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | RN89 road |
E465115
|
entity |
| Predicate | partlyDowngradedTo |
P134101
|
FINISHED |
| Object | départementale roads |
—
|
LITERAL 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: départementale roads | Statement: [RN89 road, partlyDowngradedTo, départementale roads]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partlyDowngradedTo Context triple: [RN89 road, partlyDowngradedTo, départementale roads]
-
A.
partlyUpgradedTo
Indicates that an entity has undergone an incomplete or partial upgrade to another specified state, version, or configuration.
-
B.
mayBeDowngradedTo
Indicates that one entity has the potential or permission to be reduced in status, level, or classification to another entity.
-
C.
partiallyRestored
Indicates that an entity has been brought back toward a previous or original state, but the restoration is incomplete or only partially achieved.
-
D.
partiallySupportedBy
Indicates that something receives incomplete, limited, or not fully sufficient support from another entity.
-
E.
partlyRebuilt
Indicates that an entity has been reconstructed or restored to some extent, but not fully.
- F. None of above. chosen
Provenance (4 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_69d8dd01a56c81909694a128c66b21d7 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d6a561848190bd957f248471c191 |
completed | April 20, 2026, 7:32 a.m. |
| PD | Predicate disambiguation | batch_69e4a2f88e0c81908cb20f08bf24cd32 |
completed | April 19, 2026, 9:40 a.m. |
| PDg | Predicate description generation | batch_69e4ad8e075c8190ad561edc5e520057 |
completed | April 19, 2026, 10:25 a.m. |
Created at: April 10, 2026, 12:01 p.m.