Triple
T32293018
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Service Technique du Génie |
E825016
|
entity |
| Predicate | usedStandards |
P1587
|
FINISHED |
| Object | French fortification regulations |
—
|
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: French fortification regulations | Statement: [Service Technique du Génie, usedStandards, French fortification regulations]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedStandards Context triple: [Service Technique du Génie, usedStandards, French fortification regulations]
-
A.
standardsUsedIn
Indicates that certain standards are applied, referenced, or followed within a particular context, process, or entity.
-
B.
usedAsStandard
Indicates that one entity serves as the reference or benchmark against which another entity is measured, compared, or evaluated.
-
C.
usesStandard
chosen
Indicates that one entity adopts, follows, or operates according to a specified standard defined by another entity or reference.
-
D.
primaryUsersOfStandards
Indicates that the subject entities are the main or principal users or adopters of the referenced standards.
-
E.
standardsType
Indicates the classification or category of standards that apply to or are associated with an entity or activity.
- 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_69f349101b788190b4f14884dc7d1ed2 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6bd37d61081909d62fc5486edbc13 |
completed | May 3, 2026, 3:12 a.m. |
| PD | Predicate disambiguation | batch_69f6b632cf788190a3d0c08cd026b84b |
completed | May 3, 2026, 2:42 a.m. |
Created at: May 1, 2026, 12:44 a.m.