Triple

T38377844
Position Surface form Disambiguated ID Type / Status
Subject Дворцовый мост E893673 entity
Predicate проектировщик P12117 FINISHED
Object инженер Андрей Пшеницкий
Инженер Андрей Пшеницкий — российский инженер, наиболее известный как автор проекта знаменитого разводного Дворцового моста в Санкт‑Петербурге.
 E2267821 NE FINISHED

How this triple was built (3 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: инженер Андрей Пшеницкий | Statement: [Дворцовый мост, проектировщик, инженер Андрей Пшеницкий]
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: инженер Андрей Пшеницкий
Triple: [Дворцовый мост, проектировщик, инженер Андрей Пшеницкий]
Generated description
Инженер Андрей Пшеницкий — российский инженер, наиболее известный как автор проекта знаменитого разводного Дворцового моста в Санкт‑Петербурге.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: проектировщик
Context triple: [Дворцовый мост, проектировщик, инженер Андрей Пшеницкий]
  • A. designerOccupation chosen
    Indicates that one entity serves as the professional designer or design specialist for another entity.
  • B. supervisingArchitect
    Indicates that one entity serves as the overseeing architect responsible for directing, reviewing, or approving the architectural work of another entity or project.
  • C. designerType
    Indicates the specific kind or category of designer role associated with an entity.
  • D. architectProfession
    Indicates that one entity has the profession or occupational role of an architect in relation to the other entity.
  • E. монтажёр
    Indicates that one entity serves as an editor (e.g., film or video editor) responsible for assembling and cutting together the material of another entity.
  • F. None of above.

Provenance (6 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_69f76e4b1f748190a380696a16eae4a2 completed May 3, 2026, 3:48 p.m.
NER Named-entity recognition batch_69fcd1499e2c81909bafd84dc4810f45 completed May 7, 2026, 5:52 p.m.
NED1 Entity disambiguation (via context triple) batch_6a41b2a3860c8190ab45dccdae79aa03 completed June 28, 2026, 11:47 p.m.
NEDg Description generation batch_6a41b41e4fb48190ab0e098edc14965b completed June 28, 2026, 11:54 p.m.
NED2 Entity disambiguation (via description) batch_6a41b4aff75081909d0946a1c0992447 completed June 28, 2026, 11:56 p.m.
PD Predicate disambiguation batch_69fcccf024ec819086383ffbb6cfc036 completed May 7, 2026, 5:33 p.m.
Created at: May 3, 2026, 4:31 p.m.