Triple

T23399772
Position Surface form Disambiguated ID Type / Status
Subject JC virus E559470 entity
Predicate encodesProtein P90097 FINISHED
Object VP1
VP1 is the major capsid protein of JC virus, forming the outer shell of the virion and mediating attachment to host cells.
 E1583709 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: VP1 | Statement: [JC virus, encodesProtein, VP1]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: VP1
Context triple: [JC virus, encodesProtein, VP1]
  • A. VPK
    VPK was the Soviet Union’s powerful Military-Industrial Commission responsible for overseeing and coordinating the country’s defense industry and weapons production.
  • B. VP30
    VP30 is a viral transcription factor protein of ebolaviruses that is essential for initiating and regulating the transcription of the viral genome.
  • C. ViP
    ViP is the public transport operator responsible for running tram and bus services in the German city of Potsdam.
  • D. VPZ
    VPZ is the IATA airport code for Porter County Regional Airport serving Valparaiso, Indiana.
  • E. VP9L
    VP9L is a long-slide variant of the Heckler & Koch VP9 striker-fired 9mm pistol, designed to offer improved accuracy and sight radius for competition and precision shooting.
  • 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: VP1
Triple: [JC virus, encodesProtein, VP1]
Generated description
VP1 is the major capsid protein of JC virus, forming the outer shell of the virion and mediating attachment to host cells.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: VP1
Target entity description: VP1 is the major capsid protein of JC virus, forming the outer shell of the virion and mediating attachment to host cells.
  • A. VPK
    VPK was the Soviet Union’s powerful Military-Industrial Commission responsible for overseeing and coordinating the country’s defense industry and weapons production.
  • B. VP30
    VP30 is a viral transcription factor protein of ebolaviruses that is essential for initiating and regulating the transcription of the viral genome.
  • C. ViP
    ViP is the public transport operator responsible for running tram and bus services in the German city of Potsdam.
  • D. VPZ
    VPZ is the IATA airport code for Porter County Regional Airport serving Valparaiso, Indiana.
  • E. VP9L
    VP9L is a long-slide variant of the Heckler & Koch VP9 striker-fired 9mm pistol, designed to offer improved accuracy and sight radius for competition and precision shooting.
  • 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_69e24549610c8190a069d6411ce5f661 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f1a4dedfcc8190ab93cec3c3d15c53 completed April 29, 2026, 6:27 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0c5df194bc819084aa4de85966c68f completed May 19, 2026, 12:56 p.m.
NEDg Description generation batch_6a0c5f52fe308190b87c53f9a9d915e0 completed May 19, 2026, 1:02 p.m.
NED2 Entity disambiguation (via description) batch_6a0c5ffbea40819088a5a01a3763c718 completed May 19, 2026, 1:05 p.m.
Created at: April 17, 2026, 5:37 p.m.