Triple

T1694134
Position Surface form Disambiguated ID Type / Status
Subject Tula Governorate E36616 entity
Predicate hasPart P35 FINISHED
Object Pronsky Uyezd
Pronsky Uyezd was an administrative subdivision (uyezd) of the Russian Empire, historically located within the Tula region.
E228687 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: Pronsky Uyezd | Statement: [Tula Governorate, hasPart, Pronsky Uyezd]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pronsky Uyezd
Context triple: [Tula Governorate, hasPart, Pronsky Uyezd]
  • A. Krapivensky Uyezd
    Krapivensky Uyezd was an administrative district (uyezd) of the Russian Empire located within the Tula Governorate.
  • B. Dankovsky Uyezd
    Dankovsky Uyezd was an administrative subdivision (uyezd) of the former Tula Governorate in the Russian Empire.
  • C. Chernsky Uyezd
    Chernsky Uyezd was an administrative district (uyezd) within the historical Tula Governorate of the Russian Empire.
  • D. Epifansky Uyezd
    Epifansky Uyezd was an administrative district (uyezd) within the historical Tula Governorate of the Russian Empire.
  • E. Yefremovsky Uyezd
    Yefremovsky Uyezd was an administrative subdivision (uyezd) of the Russian Empire centered around the town of Yefremov in what is now Tula Oblast.
  • 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: Pronsky Uyezd
Triple: [Tula Governorate, hasPart, Pronsky Uyezd]
Generated description
Pronsky Uyezd was an administrative subdivision (uyezd) of the Russian Empire, historically located within the Tula region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Pronsky Uyezd
Target entity description: Pronsky Uyezd was an administrative subdivision (uyezd) of the Russian Empire, historically located within the Tula region.
  • A. Krapivensky Uyezd
    Krapivensky Uyezd was an administrative district (uyezd) of the Russian Empire located within the Tula Governorate.
  • B. Dankovsky Uyezd
    Dankovsky Uyezd was an administrative subdivision (uyezd) of the former Tula Governorate in the Russian Empire.
  • C. Chernsky Uyezd
    Chernsky Uyezd was an administrative district (uyezd) within the historical Tula Governorate of the Russian Empire.
  • D. Epifansky Uyezd
    Epifansky Uyezd was an administrative district (uyezd) within the historical Tula Governorate of the Russian Empire.
  • E. Yefremovsky Uyezd
    Yefremovsky Uyezd was an administrative subdivision (uyezd) of the Russian Empire centered around the town of Yefremov in what is now Tula Oblast.
  • 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_69a886163dec8190859c514232a37a05 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69aa62b228988190a7d19003ddf10ce5 completed March 6, 2026, 5:14 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae1fbcd17c81909e6d3771442f1245 completed March 9, 2026, 1:17 a.m.
NEDg Description generation batch_69ae20cb479c8190853d0d954af16887 completed March 9, 2026, 1:22 a.m.
NED2 Entity disambiguation (via description) batch_69ae21614e74819093617a355f0857c8 completed March 9, 2026, 1:24 a.m.
Created at: March 4, 2026, 7:29 p.m.