Triple

T18392852
Position Surface form Disambiguated ID Type / Status
Subject Свирь E449779 entity
Predicate hasTownOnBank P847 FINISHED
Object Подпорожье
Подпорожье — небольшой российский город в Ленинградской области, расположенный в северной части региона и известный как центр одноимённого района.
 E1322571 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: Подпорожье | Statement: [Свирь, hasTownOnBank, Подпорожье]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Подпорожье
Context triple: [Свирь, hasTownOnBank, Подпорожье]
  • A. Pomorie
    Pomorie is a Bulgarian Black Sea coastal town and resort known for its salt production, mud therapy, and historic monastery.
  • B. На дне
    «На дне» — социально-психологическая драма Максима Горького о жизни обитателей ночлежки, ставшая классикой русской литературы и театра.
  • C. Gate of the Sea
    Gate of the Sea is a historic city gate in Tunis, Tunisia, that once marked the boundary between the old medina and the modern European-style city.
  • D. Night Sea
    "Night Sea" is a minimalist abstract painting by Agnes Martin, exemplifying her serene grid-based style and meditative exploration of subtle color and line.
  • E. Am Meer
    "Am Meer" is a German art song composed by Franz Schubert, best known as one of the settings in his posthumously published song cycle "Schwanengesang."
  • 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: Подпорожье
Triple: [Свирь, hasTownOnBank, Подпорожье]
Generated description
Подпорожье — небольшой российский город в Ленинградской области, расположенный в северной части региона и известный как центр одноимённого района.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Подпорожье
Target entity description: Подпорожье — небольшой российский город в Ленинградской области, расположенный в северной части региона и известный как центр одноимённого района.
  • A. Pomorie
    Pomorie is a Bulgarian Black Sea coastal town and resort known for its salt production, mud therapy, and historic monastery.
  • B. На дне
    «На дне» — социально-психологическая драма Максима Горького о жизни обитателей ночлежки, ставшая классикой русской литературы и театра.
  • C. Gate of the Sea
    Gate of the Sea is a historic city gate in Tunis, Tunisia, that once marked the boundary between the old medina and the modern European-style city.
  • D. Night Sea
    "Night Sea" is a minimalist abstract painting by Agnes Martin, exemplifying her serene grid-based style and meditative exploration of subtle color and line.
  • E. Am Meer
    "Am Meer" is a German art song composed by Franz Schubert, best known as one of the settings in his posthumously published song cycle "Schwanengesang."
  • 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_69d8b9fab8a8819086a9ddc0871715e0 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e51844c1ec81909ec215db9b29612d completed April 19, 2026, 6 p.m.
NED1 Entity disambiguation (via context triple) batch_6a03e23eac3081909deb4a491da08bac completed May 13, 2026, 2:30 a.m.
NEDg Description generation batch_6a03e46859d481909c2738b6f47ea7b3 completed May 13, 2026, 2:39 a.m.
NED2 Entity disambiguation (via description) batch_6a03e4b743688190a582fef43f7b1956 completed May 13, 2026, 2:40 a.m.
Created at: April 10, 2026, 10:46 a.m.