Triple
T195378
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Biogen |
E3807
|
entity |
| Predicate | hasProduct |
P3585
|
FINISHED |
| Object |
Aduhelm
Aduhelm is an Alzheimer’s disease drug developed by Biogen that targets amyloid-beta plaques in the brain.
|
E24938
|
NE FINISHED |
How this triple was built (4 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: Aduhelm | Statement: [Biogen, hasProduct, Aduhelm]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Aduhelm Context triple: [Biogen, hasProduct, Aduhelm]
-
A.
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.
-
B.
Biogen
Biogen is a major American biotechnology company known for developing therapies for neurological and neurodegenerative diseases.
-
C.
Plegridy
Plegridy is a pegylated interferon beta-1a medication used to treat relapsing forms of multiple sclerosis.
-
D.
MCI-Shirley
MCI-Shirley is a medium- and minimum-security state prison for men located in Shirley, Massachusetts.
-
E.
Neuralink
Neuralink is a neurotechnology company developing implantable brain–computer interfaces aimed at enabling direct communication between the human brain and computers.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Aduhelm Triple: [Biogen, hasProduct, Aduhelm]
Generated description
Aduhelm is an Alzheimer’s disease drug developed by Biogen that targets amyloid-beta plaques in the brain.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Aduhelm Target entity description: Aduhelm is an Alzheimer’s disease drug developed by Biogen that targets amyloid-beta plaques in the brain.
-
A.
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.
-
B.
Biogen
Biogen is a major American biotechnology company known for developing therapies for neurological and neurodegenerative diseases.
-
C.
Plegridy
Plegridy is a pegylated interferon beta-1a medication used to treat relapsing forms of multiple sclerosis.
-
D.
MCI-Shirley
MCI-Shirley is a medium- and minimum-security state prison for men located in Shirley, Massachusetts.
-
E.
Neuralink
Neuralink is a neurotechnology company developing implantable brain–computer interfaces aimed at enabling direct communication between the human brain and computers.
- F. None of above. chosen
Provenance (5 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_69a25969425081908e178db8ba4631c2 |
completed | Feb. 28, 2026, 2:56 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a3161cdc4c8190bc67683a1a5d39d9 |
completed | Feb. 28, 2026, 4:21 p.m. |
| NEDg | Description generation | batch_69a31677d5c48190967cacd20fd6357a |
completed | Feb. 28, 2026, 4:23 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69a316d53594819095710388c11624eb |
completed | Feb. 28, 2026, 4:24 p.m. |
Created at: Feb. 28, 2026, 2:41 a.m.