Triple
T27084156
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | National roads in France |
E685988
|
entity |
| Predicate | typicalNumberingFormat |
P181640
|
FINISHED |
| Object | Nxx |
—
|
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: Nxx | Statement: [National roads in France, typicalNumberingFormat, Nxx]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalNumberingFormat Context triple: [National roads in France, typicalNumberingFormat, Nxx]
-
A.
numberingType
Indicates the scheme or style used to assign sequential numbers or labels within an ordered set.
-
B.
standardNumberingScheme
Indicates that there is a specific, commonly accepted numbering system or convention being applied to identify or order the related entities.
-
C.
hasNumberingFormat
chosen
Indicates that an entity uses or is associated with a particular scheme or style for numbering items, elements, or positions.
-
D.
identificationNumberFormat
Indicates the specific structural pattern or rules that an identification number must follow.
-
E.
followsNumbering
Indicates that one entity adheres to or continues the numbering sequence established by another entity.
- F. None of above.
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_69ef148940ec819097b5c20fbfbf7c81 |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69ff6fba1a5c8190a660279a6271d785 |
completed | May 9, 2026, 5:32 p.m. |
| PD | Predicate disambiguation | batch_69ff6f59388c8190a7d6ab7bc7705bc0 |
completed | May 9, 2026, 5:31 p.m. |
Created at: April 27, 2026, 8:36 a.m.