Triple
T195397
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Biogen |
E3807
|
entity |
| Predicate | hasNotableDrug |
P7501
|
FINISHED |
| Object | Tysabri |
E24936
|
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: Tysabri | Statement: [Biogen, hasNotableDrug, Tysabri]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tysabri Context triple: [Biogen, hasNotableDrug, Tysabri]
-
A.
Tysabri
chosen
Tysabri is a monoclonal antibody medication primarily used to treat relapsing forms of multiple sclerosis and Crohn’s disease.
-
B.
Tecfidera
Tecfidera is an oral disease-modifying medication used to treat relapsing forms of multiple sclerosis by reducing inflammation and relapse frequency.
-
C.
Aduhelm
Aduhelm is an Alzheimer’s disease drug developed by Biogen that targets amyloid-beta plaques in the brain.
-
D.
Spinraza
Spinraza is a prescription medication used to treat spinal muscular atrophy (SMA) by modifying SMN2 gene expression to increase production of survival motor neuron (SMN) protein.
-
E.
Vumerity
Vumerity is an oral prescription medication used to treat relapsing forms of multiple sclerosis in adults.
- 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_69a2548debd48190ae3a06d6e65b53c6 |
completed | Feb. 28, 2026, 2:35 a.m. |
| NER | Named-entity recognition | batch_69a25bc96aa081908ef74c9827c9aa48 |
completed | Feb. 28, 2026, 3:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a32812176c8190987df03dc08b47a9 |
completed | Feb. 28, 2026, 5:38 p.m. |
Created at: Feb. 28, 2026, 2:41 a.m.