Triple

T10609981
Position Surface form Disambiguated ID Type / Status
Subject Dravet syndrome E275979 entity
Predicate hasTreatment P4714 FINISHED
Object topiramate
Topiramate is an anticonvulsant medication commonly used to treat various forms of epilepsy and prevent migraines.
 E874309 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: topiramate | Statement: [Dravet syndrome, hasTreatment, topiramate]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: topiramate
Context triple: [Dravet syndrome, hasTreatment, topiramate]
  • A. carbamazepine
    Carbamazepine is an anticonvulsant and mood-stabilizing drug commonly used to treat epilepsy, trigeminal neuralgia, and bipolar disorder.
  • B. phenytoin
    Phenytoin is an antiepileptic medication commonly used to prevent and control seizures by stabilizing neuronal activity in the brain.
  • C. Andexxa
    Andexxa is a recombinant modified human factor Xa protein used as a reversal agent to counteract the anticoagulant effects of factor Xa inhibitors such as rivaroxaban and apixaban.
  • D. Lyrica
    Lyrica is a prescription medication (pregabalin) commonly used to treat nerve pain, fibromyalgia, and certain types of seizures.
  • E. Anpezan
    Anpezan is a regional dialect of the Ladin language spoken in parts of the Dolomite area of northern Italy.
  • 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: topiramate
Triple: [Dravet syndrome, hasTreatment, topiramate]
Generated description
Topiramate is an anticonvulsant medication commonly used to treat various forms of epilepsy and prevent migraines.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: topiramate
Target entity description: Topiramate is an anticonvulsant medication commonly used to treat various forms of epilepsy and prevent migraines.
  • A. carbamazepine
    Carbamazepine is an anticonvulsant and mood-stabilizing drug commonly used to treat epilepsy, trigeminal neuralgia, and bipolar disorder.
  • B. phenytoin
    Phenytoin is an antiepileptic medication commonly used to prevent and control seizures by stabilizing neuronal activity in the brain.
  • C. Andexxa
    Andexxa is a recombinant modified human factor Xa protein used as a reversal agent to counteract the anticoagulant effects of factor Xa inhibitors such as rivaroxaban and apixaban.
  • D. Lyrica
    Lyrica is a prescription medication (pregabalin) commonly used to treat nerve pain, fibromyalgia, and certain types of seizures.
  • E. Anpezan
    Anpezan is a regional dialect of the Ladin language spoken in parts of the Dolomite area of northern Italy.
  • 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_69d6aaf948d88190806cc3a8c47a3fb2 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d6df59468881909b0c67d3f08c4b76 completed April 8, 2026, 11:06 p.m.
NED1 Entity disambiguation (via context triple) batch_69d95ebe539881908aeff1cd65cf925f completed April 10, 2026, 8:34 p.m.
NEDg Description generation batch_69d95f81955c8190b629d57a034a4b76 completed April 10, 2026, 8:37 p.m.
NED2 Entity disambiguation (via description) batch_69d961047a78819088094e02c0b99f60 completed April 10, 2026, 8:43 p.m.
Created at: April 8, 2026, 7:32 p.m.