Triple
T4260419
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ephedra |
E96088
|
entity |
| Predicate | reasonForRegulation |
P54347
|
FINISHED |
| Object | risk of cardiovascular adverse events |
—
|
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: risk of cardiovascular adverse events | Statement: [Ephedra, reasonForRegulation, risk of cardiovascular adverse events]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reasonForRegulation Context triple: [Ephedra, reasonForRegulation, risk of cardiovascular adverse events]
-
A.
regulationReason
chosen
Indicates the reason or justification for which a regulation is established, applied, or enforced in relation to an entity or activity.
-
B.
regulationAtIssue
Indicates that a specific regulation is the subject of concern, dispute, or analysis in the given context.
-
C.
allowsRegulationOf
Indicates that one entity grants the authority, means, or conditions for another entity to control, manage, or govern something.
-
D.
subjectToRegulation
Indicates that an entity is governed, constrained, or controlled by a specific rule, law, or regulatory framework.
-
E.
supportsRegulation
Indicates that one entity endorses, backs, or advocates for the implementation or continuation of a specific regulation.
- 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_69b3454095ac81909c2494f7ff294af1 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b34f8103b48190934a810faafa6cb7 |
completed | March 12, 2026, 11:42 p.m. |
| PD | Predicate disambiguation | batch_69b347f73e008190a908a48ef389945a |
completed | March 12, 2026, 11:10 p.m. |
Created at: March 12, 2026, 11:06 p.m.