Triple
T19772809
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lipitor |
E474929
|
entity |
| Predicate | hasGeneric |
P125213
|
FINISHED |
| Object | atorvastatin generic formulations |
—
|
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: atorvastatin generic formulations | Statement: [Lipitor, hasGeneric, atorvastatin generic formulations]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasGeneric Context triple: [Lipitor, hasGeneric, atorvastatin generic formulations]
-
A.
hasGenericName
Indicates that an entity is associated with a non-brand, generic name that designates its general type or class.
-
B.
isGenericOver
Indicates that one entity is defined or parameterized in terms of another, more specific entity, such that it can operate over or apply to that entity as a generic.
-
C.
isGenericAvailable
chosen
Indicates that a non-brand (generic) version of a product, typically a medication, is available as an alternative.
-
D.
hasTypeGenus
Indicates that one entity is the type genus that formally defines or represents the taxonomic group of the other entity.
-
E.
isGenericConstraintExample
Indicates that one entity serves as an example or illustration of a generic type constraint applied to 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_69d8e51a43a08190956bc6df13c91a77 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6535ce4d08190a1dfca2df95a8631 |
completed | April 20, 2026, 4:25 p.m. |
| PD | Predicate disambiguation | batch_69e53053ed2881908400becdfada7fd3 |
completed | April 19, 2026, 7:43 p.m. |
Created at: April 10, 2026, 1:48 p.m.