Triple

T14813761
Position Surface form Disambiguated ID Type / Status
Subject Tvertsa River E348253 entity
Predicate hasRussianName P20560 FINISHED
Object Тверца
Тверца — река в Тверской области России, являющаяся притоком Волги и проходящая через город Торжок.
 E1120466 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: Тверца | Statement: [Tvertsa River, hasRussianName, Тверца]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Тверца
Context triple: [Tvertsa River, hasRussianName, Тверца]
  • A. Smolenskin
    Smolenskin is the surname of Peretz Smolenskin, a prominent 19th-century Hebrew novelist and key figure in the Jewish Enlightenment (Haskalah) movement.
  • B. Terebovlia
    Terebovlia is a historic town in western Ukraine known for its medieval fortress ruins and role as a regional cultural center.
  • C. Zemtsov
    Zemtsov is a Russian surname most notably borne by violist Mikhail Zemtsov.
  • D. Staritsa
    Staritsa is a historic town in Tver Oblast, Russia, known for its medieval monasteries and role as a regional center in the upper Volga region.
  • E. Orlovets
    Orlovets is a prominent mountain peak in Bulgaria’s Rila Mountains, popular with hikers and climbers for its rugged alpine terrain and scenic views.
  • 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: Тверца
Triple: [Tvertsa River, hasRussianName, Тверца]
Generated description
Тверца — река в Тверской области России, являющаяся притоком Волги и проходящая через город Торжок.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Тверца
Target entity description: Тверца — река в Тверской области России, являющаяся притоком Волги и проходящая через город Торжок.
  • A. Smolenskin
    Smolenskin is the surname of Peretz Smolenskin, a prominent 19th-century Hebrew novelist and key figure in the Jewish Enlightenment (Haskalah) movement.
  • B. Terebovlia
    Terebovlia is a historic town in western Ukraine known for its medieval fortress ruins and role as a regional cultural center.
  • C. Zemtsov
    Zemtsov is a Russian surname most notably borne by violist Mikhail Zemtsov.
  • D. Staritsa
    Staritsa is a historic town in Tver Oblast, Russia, known for its medieval monasteries and role as a regional center in the upper Volga region.
  • E. Orlovets
    Orlovets is a prominent mountain peak in Bulgaria’s Rila Mountains, popular with hikers and climbers for its rugged alpine terrain and scenic views.
  • 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_69d822eb8f588190bf53445e730a934f completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69decfe0e89c81908c0e1fe2bc3ebcfc completed April 14, 2026, 11:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe24cca0b88190b20a6c7dd77b8146 completed May 8, 2026, 6 p.m.
NEDg Description generation batch_69fe291c69fc8190b29d6d2ca89ce6ec completed May 8, 2026, 6:19 p.m.
NED2 Entity disambiguation (via description) batch_69fe29a093d0819092ae65dc66a3c190 completed May 8, 2026, 6:21 p.m.
Created at: April 10, 2026, 1:48 a.m.