Triple

T18896339
Position Surface form Disambiguated ID Type / Status
Subject PSINet Stadium E462217 entity
Predicate sponsor P67 FINISHED
Object PSINet
PSINet was an early major commercial internet service provider that became prominent during the dot-com era before declaring bankruptcy in the early 2000s.
 E1348321 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: PSINet | Statement: [PSINet Stadium, sponsor, PSINet]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: PSINet
Context triple: [PSINet Stadium, sponsor, PSINet]
  • A. SISNeT
    SISNeT is a system that provides satellite navigation augmentation data, similar in purpose and function to the European Geostationary Navigation Overlay Service (EGNOS).
  • B. PSI
    PSI is the acronym commonly used for the Italian Socialist Party, a historic socialist political party in Italy.
  • C. PSI
    PSI is a major Swiss research institute specializing in natural and engineering sciences, particularly known for its large-scale facilities in particle physics, materials science, and energy research.
  • D. PSI
    PSI is a global federation of public sector trade unions that advocates for quality public services and workers’ rights worldwide.
  • E. PNN
    PNN is the London Stock Exchange ticker symbol for Pennon Group, a UK-based water utility and environmental infrastructure company.
  • 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: PSINet
Triple: [PSINet Stadium, sponsor, PSINet]
Generated description
PSINet was an early major commercial internet service provider that became prominent during the dot-com era before declaring bankruptcy in the early 2000s.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: PSINet
Target entity description: PSINet was an early major commercial internet service provider that became prominent during the dot-com era before declaring bankruptcy in the early 2000s.
  • A. SISNeT
    SISNeT is a system that provides satellite navigation augmentation data, similar in purpose and function to the European Geostationary Navigation Overlay Service (EGNOS).
  • B. PSI
    PSI is the acronym commonly used for the Italian Socialist Party, a historic socialist political party in Italy.
  • C. PSI
    PSI is a major Swiss research institute specializing in natural and engineering sciences, particularly known for its large-scale facilities in particle physics, materials science, and energy research.
  • D. PSI
    PSI is a global federation of public sector trade unions that advocates for quality public services and workers’ rights worldwide.
  • E. PNN
    PNN is the London Stock Exchange ticker symbol for Pennon Group, a UK-based water utility and environmental infrastructure company.
  • 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_69d8dcfd05bc819088903cca13cc2846 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5c47f6c948190918ade08bb88f1fd completed April 20, 2026, 6:15 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0582b91a448190b080d3c9c958f2b2 completed May 14, 2026, 8:07 a.m.
NEDg Description generation batch_6a0588c516ec81908d6939f447e7f590 completed May 14, 2026, 8:33 a.m.
NED2 Entity disambiguation (via description) batch_6a0589612cbc819086bccc55658921e0 completed May 14, 2026, 8:35 a.m.
Created at: April 10, 2026, 11:58 a.m.