Triple
T1172272
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eisai |
E24939
|
entity |
| Predicate | developed |
P73
|
FINISHED |
| Object | Aricept |
E133125
|
NE 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: Aricept | Statement: [Eisai, developed, Aricept]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Aricept Context triple: [Eisai, developed, Aricept]
-
A.
Donepezil
chosen
Donepezil is a cholinesterase inhibitor medication primarily used to treat cognitive symptoms of Alzheimer's disease.
-
B.
rivastigmine
Rivastigmine is a cholinesterase inhibitor medication used to manage symptoms of mild to moderate dementia, particularly in Alzheimer's and Parkinson's disease.
-
C.
memantine
Memantine is a medication that helps manage symptoms of moderate to severe Alzheimer's disease by modulating glutamate activity in the brain.
-
D.
Aduhelm
Aduhelm is an Alzheimer’s disease drug developed by Biogen that targets amyloid-beta plaques in the brain.
-
E.
riluzole
Riluzole is a neuroprotective medication that modestly prolongs survival and slows disease progression in people with amyotrophic lateral sclerosis (ALS).
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69a494082a7c819095004f423f294a64 |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4bcecab688190b21a926874cd98d1 |
completed | March 1, 2026, 10:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ac7f323bbc8190a55fe2101f9561e2 |
completed | March 7, 2026, 7:40 p.m. |
Created at: March 1, 2026, 7:45 p.m.