Triple
T27640016
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | E-meter |
E696563
|
entity |
| Predicate | previouslyRegulatedAs |
P59373
|
FINISHED |
| Object | medical device by the U.S. FDA |
—
|
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: medical device by the U.S. FDA | Statement: [E-meter, previouslyRegulatedAs, medical device by the U.S. FDA]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: previouslyRegulatedAs Context triple: [E-meter, previouslyRegulatedAs, medical device by the U.S. FDA]
-
A.
formerlyRegulatedBy
chosen
Indicates that an entity was previously subject to the authority or control of a particular regulator, but is no longer regulated by that entity.
-
B.
predecessorRegulation
Indicates that one regulation directly precedes and is replaced or superseded by another regulation in a legal or regulatory sequence.
-
C.
previouslyLicensedAs
Indicates that an entity held a license under a different name or status at some earlier time.
-
D.
previouslyAbolished
Indicates that something was officially ended, discontinued, or annulled at some point in the past.
-
E.
regulatoryType
Indicates the specific kind or category of regulatory control, rule, or oversight that applies in the given relationship.
- 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_69ef5909f3848190805f35b76833e722 |
completed | April 27, 2026, 12:39 p.m. |
| NER | Named-entity recognition | batch_69fbaebc8f2c8190b94f1b4a3ec92e8c |
completed | May 6, 2026, 9:12 p.m. |
| PD | Predicate disambiguation | batch_69fbadf1e6008190a71bbd196ba06844 |
completed | May 6, 2026, 9:09 p.m. |
Created at: April 27, 2026, 2:25 p.m.