Triple

T5981292
Position Surface form Disambiguated ID Type / Status
Subject progressive multifocal leukoencephalopathy E133122 entity
Predicate hasPathogen P2897 FINISHED
Object JC virus
JC virus is a human polyomavirus that typically causes asymptomatic infection but can lead to severe demyelinating brain disease in immunocompromised individuals.
 E559470 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: JC virus | Statement: [progressive multifocal leukoencephalopathy, hasPathogen, JC virus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: JC virus
Context triple: [progressive multifocal leukoencephalopathy, hasPathogen, JC virus]
  • A. EBV
    EBV is the National Rail station code for Ebbw Vale Parkway railway station in Wales.
  • B. KHV
    KHV is the IATA airport code for Khabarovsk Novy Airport, a major air transport hub serving the city of Khabarovsk in Russia’s Far East.
  • C. Ebolavirus
    Ebolavirus is a genus of filamentous, enveloped RNA viruses in the Filoviridae family that cause severe and often fatal hemorrhagic fever in humans and other primates.
  • D. MHV
    MHV is the IATA airport code for Mojave Air and Space Port, a well-known aerospace testing and flight facility in Mojave, California.
  • E. Vircava
    Vircava is a river in Latvia that serves as one of the tributaries feeding into the larger Lielupe River system.
  • 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: JC virus
Triple: [progressive multifocal leukoencephalopathy, hasPathogen, JC virus]
Generated description
JC virus is a human polyomavirus that typically causes asymptomatic infection but can lead to severe demyelinating brain disease in immunocompromised individuals.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: JC virus
Target entity description: JC virus is a human polyomavirus that typically causes asymptomatic infection but can lead to severe demyelinating brain disease in immunocompromised individuals.
  • A. EBV
    EBV is the National Rail station code for Ebbw Vale Parkway railway station in Wales.
  • B. KHV
    KHV is the IATA airport code for Khabarovsk Novy Airport, a major air transport hub serving the city of Khabarovsk in Russia’s Far East.
  • C. Ebolavirus
    Ebolavirus is a genus of filamentous, enveloped RNA viruses in the Filoviridae family that cause severe and often fatal hemorrhagic fever in humans and other primates.
  • D. MHV
    MHV is the IATA airport code for Mojave Air and Space Port, a well-known aerospace testing and flight facility in Mojave, California.
  • E. Vircava
    Vircava is a river in Latvia that serves as one of the tributaries feeding into the larger Lielupe River system.
  • 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_69c0086f45e8819098f73dd16d45ec9d completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c04a67c3248190ba35a7121eb49672 completed March 22, 2026, 8 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0e42174a88190b8b40cbc7815911f completed March 23, 2026, 6:56 a.m.
NEDg Description generation batch_69c0f602b79881909a6d971972f760b1 completed March 23, 2026, 8:12 a.m.
NED2 Entity disambiguation (via description) batch_69c0f6a75b908190b35d13b9593cf21f completed March 23, 2026, 8:15 a.m.
Created at: March 22, 2026, 4:04 p.m.