Triple

T22773795
Position Surface form Disambiguated ID Type / Status
Subject Smolensk fortress wall E563634 entity
Predicate hasSection P35 FINISHED
Object Zadneprovskaya Tower
Zadneprovskaya Tower is a historic defensive tower that forms part of the Smolensk fortress wall in Smolensk, Russia.
E1554950 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: Zadneprovskaya Tower | Statement: [Smolensk fortress wall, hasSection, Zadneprovskaya Tower]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Zadneprovskaya Tower
Context triple: [Smolensk fortress wall, hasSection, Zadneprovskaya Tower]
  • A. Donetskaya Tower
    Donetskaya Tower is a historic defensive tower that forms part of the Smolensk fortress wall in Smolensk, Russia.
  • B. Dmitrovskaya Tower
    Dmitrovskaya Tower is a prominent historic defensive tower and main entrance gate of the Nizhny Novgorod Kremlin in Russia.
  • C. Koromyslova Tower
    Koromyslova Tower is a historic defensive tower and one of the prominent architectural features of the Nizhny Novgorod Kremlin in Russia.
  • D. Granovitaya Tower
    Granovitaya Tower is a historic defensive tower that forms part of the medieval Kolomna Kremlin fortress in Russia.
  • E. Danube Tower
    Danube Tower is a prominent observation and telecommunications tower in Vienna, Austria, known for its panoramic city views and revolving restaurant.
  • 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: Zadneprovskaya Tower
Triple: [Smolensk fortress wall, hasSection, Zadneprovskaya Tower]
Generated description
Zadneprovskaya Tower is a historic defensive tower that forms part of the Smolensk fortress wall in Smolensk, Russia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Zadneprovskaya Tower
Target entity description: Zadneprovskaya Tower is a historic defensive tower that forms part of the Smolensk fortress wall in Smolensk, Russia.
  • A. Donetskaya Tower
    Donetskaya Tower is a historic defensive tower that forms part of the Smolensk fortress wall in Smolensk, Russia.
  • B. Dmitrovskaya Tower
    Dmitrovskaya Tower is a prominent historic defensive tower and main entrance gate of the Nizhny Novgorod Kremlin in Russia.
  • C. Koromyslova Tower
    Koromyslova Tower is a historic defensive tower and one of the prominent architectural features of the Nizhny Novgorod Kremlin in Russia.
  • D. Granovitaya Tower
    Granovitaya Tower is a historic defensive tower that forms part of the medieval Kolomna Kremlin fortress in Russia.
  • E. Danube Tower
    Danube Tower is a prominent observation and telecommunications tower in Vienna, Austria, known for its panoramic city views and revolving restaurant.
  • 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_69e24554497c819080b996e071de27c2 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17b6040048190a36fa759e06136ea completed April 29, 2026, 3:30 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b9e8c5aac8190b3c9d22676205c8e completed May 18, 2026, 11:19 p.m.
NEDg Description generation batch_6a0b9f73032481908f0df881801de5b2 completed May 18, 2026, 11:23 p.m.
NED2 Entity disambiguation (via description) batch_6a0ba068def08190b22058cf5bd76b4f completed May 18, 2026, 11:27 p.m.
Created at: April 17, 2026, 3:27 p.m.