Triple
T32880592
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SNCF Fret |
E841051
|
entity |
| Predicate | hasSafetyRegime |
P34675
|
FINISHED |
| Object | European railway safety 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: European railway safety regulations | Statement: [SNCF Fret, hasSafetyRegime, European railway safety regulations]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSafetyRegime Context triple: [SNCF Fret, hasSafetyRegime, European railway safety regulations]
-
A.
hasSecurityRegime
Indicates that an entity is governed, protected, or controlled by a particular security regime, framework, or set of security rules.
-
B.
hasSafetyRegulationCompliance
Indicates that an entity adheres to, satisfies, or is in conformity with specified safety regulations or standards.
-
C.
hasRegulations
chosen
Indicates that one entity imposes, contains, or is associated with rules or regulatory requirements that govern the behavior or operation of another entity.
-
D.
hasSafetyCertificate
Indicates that an entity possesses or has been granted a valid safety certificate.
-
E.
hasSafetyReputation
Indicates that one entity is associated with an assessment or record of safety-related reliability or trustworthiness.
- 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_69f349446e288190a70c05bcc4d81172 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f791cc969c8190bf187d6031a030d5 |
completed | May 3, 2026, 6:19 p.m. |
| PD | Predicate disambiguation | batch_69f791033d288190b118029fe412b9c9 |
completed | May 3, 2026, 6:16 p.m. |
Created at: May 1, 2026, 1:18 a.m.