Triple
T5114924
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Memantine |
E115307
|
entity |
| Predicate | wasFirstApprovedForAlzheimersIn |
P24561
|
FINISHED |
| Object | Europe in the 1980s |
—
|
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: Europe in the 1980s | Statement: [Memantine, wasFirstApprovedForAlzheimersIn, Europe in the 1980s]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasFirstApprovedForAlzheimersIn Context triple: [Memantine, wasFirstApprovedForAlzheimersIn, Europe in the 1980s]
-
A.
isFirstDrugApprovedFor
chosen
Indicates that a drug is the earliest or original medication approved for treating a particular condition, disease, or indication.
-
B.
firstTestedBy
Indicates that an item, concept, or process was initially tested or tried out by a particular agent or entity.
-
C.
saidToBeTheFirst
Indicates that one entity is claimed or regarded as being the earliest or original instance of something relative to others.
-
D.
wasFirstObservedIn
Indicates that an entity was initially noticed, recorded, or detected at a particular time or place.
-
E.
regulatoryApprovalYear
Indicates the calendar year in which an official regulatory body granted approval for the referenced item, action, or 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_69bd4441d1648190a54a533895041987 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd75ce6044819094166aebf0688665 |
completed | March 20, 2026, 4:29 p.m. |
| PD | Predicate disambiguation | batch_69bd715fe3a8819087d3065adddba515 |
completed | March 20, 2026, 4:10 p.m. |
Created at: March 20, 2026, 1:41 p.m.