Triple

T2489530
Position Surface form Disambiguated ID Type / Status
Subject Cossacks E52005 entity
Predicate usesInstitution P23672 FINISHED
Object Krug
Krug is the traditional Cossack communal assembly that served as their highest decision-making and self-governing body.
 E272676 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: Krug | Statement: [Cossacks, usesInstitution, Krug]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Krug
Context triple: [Cossacks, usesInstitution, Krug]
  • A. Hennessy
    Hennessy is a surname most prominently associated with John L. Hennessy, a renowned computer scientist and former president of Stanford University.
  • B. Kavalan
    Kavalan is an indigenous Austronesian language of Taiwan, traditionally spoken by the Kavalan people on the island’s northeastern coast.
  • C. Carling
    Carling is a major British beer brand known for its long-standing sponsorship of top-tier English football competitions and awards.
  • D. Ballantine
    Ballantine is the surname of the individual after whom the prestigious Stuart Ballantine Medal for scientific and engineering achievement is named.
  • E. Seelter Buund
    Seelter Buund is an organization dedicated to preserving and promoting the Saterland Frisian language and culture.
  • 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: Krug
Triple: [Cossacks, usesInstitution, Krug]
Generated description
Krug is the traditional Cossack communal assembly that served as their highest decision-making and self-governing body.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Krug
Target entity description: Krug is the traditional Cossack communal assembly that served as their highest decision-making and self-governing body.
  • A. Hennessy
    Hennessy is a surname most prominently associated with John L. Hennessy, a renowned computer scientist and former president of Stanford University.
  • B. Kavalan
    Kavalan is an indigenous Austronesian language of Taiwan, traditionally spoken by the Kavalan people on the island’s northeastern coast.
  • C. Carling
    Carling is a major British beer brand known for its long-standing sponsorship of top-tier English football competitions and awards.
  • D. Ballantine
    Ballantine is the surname of the individual after whom the prestigious Stuart Ballantine Medal for scientific and engineering achievement is named.
  • E. Seelter Buund
    Seelter Buund is an organization dedicated to preserving and promoting the Saterland Frisian language and culture.
  • 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_69ab4955111c8190835bf619adec21ff completed March 6, 2026, 9:38 p.m.
NER Named-entity recognition batch_69abd82f2020819086bbd321a750ce43 completed March 7, 2026, 7:47 a.m.
NED1 Entity disambiguation (via context triple) batch_69af1f8ee974819082a2a29f8b72d131 completed March 9, 2026, 7:29 p.m.
NEDg Description generation batch_69af201e1a748190905bb221fc5dd01e completed March 9, 2026, 7:31 p.m.
NED2 Entity disambiguation (via description) batch_69af20ad25588190b8e26e82baba731d completed March 9, 2026, 7:34 p.m.
Created at: March 6, 2026, 9:45 p.m.