Triple
T15982895
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vertex Pharmaceuticals |
E387617
|
entity |
| Predicate | brandName |
P1500
|
FINISHED |
| Object |
Symdeko
Symdeko is a prescription combination therapy developed by Vertex Pharmaceuticals for the treatment of certain forms of cystic fibrosis.
|
E1188103
|
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: Symdeko | Statement: [Vertex Pharmaceuticals, brandName, Symdeko]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Symdeko Context triple: [Vertex Pharmaceuticals, brandName, Symdeko]
-
A.
Sicogi
Sicogi is a residential neighborhood located in the Marcory commune of Abidjan, Côte d'Ivoire.
-
B.
Vabysmo
Vabysmo is the brand name for faricimab, an injectable eye medication used to treat retinal diseases such as neovascular (wet) age-related macular degeneration and diabetic macular edema.
-
C.
Sikma
Sikma is a surname most notably associated with Jack Sikma, a Hall of Fame American basketball player known for his successful NBA career with the Seattle SuperSonics.
-
D.
Dek
Dek is a short or informal nickname commonly used for someone named Derek.
-
E.
Neudeck
Neudeck is a village in former East Prussia (now Ogrodzieniec in Poland) historically known as the family estate and place of death of German President and World War I field marshal Paul von Hindenburg.
- 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: Symdeko Triple: [Vertex Pharmaceuticals, brandName, Symdeko]
Generated description
Symdeko is a prescription combination therapy developed by Vertex Pharmaceuticals for the treatment of certain forms of cystic fibrosis.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Symdeko Target entity description: Symdeko is a prescription combination therapy developed by Vertex Pharmaceuticals for the treatment of certain forms of cystic fibrosis.
-
A.
Sicogi
Sicogi is a residential neighborhood located in the Marcory commune of Abidjan, Côte d'Ivoire.
-
B.
Vabysmo
Vabysmo is the brand name for faricimab, an injectable eye medication used to treat retinal diseases such as neovascular (wet) age-related macular degeneration and diabetic macular edema.
-
C.
Sikma
Sikma is a surname most notably associated with Jack Sikma, a Hall of Fame American basketball player known for his successful NBA career with the Seattle SuperSonics.
-
D.
Dek
Dek is a short or informal nickname commonly used for someone named Derek.
-
E.
Neudeck
Neudeck is a village in former East Prussia (now Ogrodzieniec in Poland) historically known as the family estate and place of death of German President and World War I field marshal Paul von Hindenburg.
- 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_69d86da94ccc819083d187f5dc6a123e |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e15755b5548190acfa29eecb11e675 |
completed | April 16, 2026, 9:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffc3cdf7848190848e9081027dc027 |
completed | May 9, 2026, 11:31 p.m. |
| NEDg | Description generation | batch_69ffc5669c1c81909bacf61c96cb7816 |
completed | May 9, 2026, 11:38 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ffc5c7db1c8190b4e1de6f6e3ce8a0 |
completed | May 9, 2026, 11:39 p.m. |
Created at: April 10, 2026, 4:54 a.m.