Triple

T722371
Position Surface form Disambiguated ID Type / Status
Subject PT-91 Twardy E14645 entity
Predicate manufacturer P490 FINISHED
Object Bumar-Łabędy
Bumar-Łabędy is a Polish defense manufacturer best known for producing armored vehicles and modernized main battle tanks.
E95333 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: Bumar-Łabędy | Statement: [PT-91 Twardy, manufacturer, Bumar-Łabędy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bumar-Łabędy
Context triple: [PT-91 Twardy, manufacturer, Bumar-Łabędy]
  • A. Ciechocinek
    Ciechocinek is a Polish spa town renowned for its historic saline graduation towers and therapeutic health resorts.
  • B. Skawina
    Skawina is a town in southern Poland near Kraków, known for its industrial facilities and role as a local economic and transport hub.
  • C. Bochnia
    Bochnia is a historic town in southern Poland best known for its medieval salt mine, one of the oldest in Europe.
  • D. Walewice
    Walewice is a village in central Poland, historically notable as the birthplace of statesman and diplomat Alexandre Colonna-Walewski, the son of Napoleon Bonaparte and Countess Maria Walewska.
  • E. Dolina Chochołowska
    Dolina Chochołowska is the largest and one of the most scenic valleys in the Polish Tatra Mountains, known for its extensive hiking trails and spring crocus blooms.
  • 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: Bumar-Łabędy
Triple: [PT-91 Twardy, manufacturer, Bumar-Łabędy]
Generated description
Bumar-Łabędy is a Polish defense manufacturer best known for producing armored vehicles and modernized main battle tanks.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Bumar-Łabędy
Target entity description: Bumar-Łabędy is a Polish defense manufacturer best known for producing armored vehicles and modernized main battle tanks.
  • A. Ciechocinek
    Ciechocinek is a Polish spa town renowned for its historic saline graduation towers and therapeutic health resorts.
  • B. Skawina
    Skawina is a town in southern Poland near Kraków, known for its industrial facilities and role as a local economic and transport hub.
  • C. Bochnia
    Bochnia is a historic town in southern Poland best known for its medieval salt mine, one of the oldest in Europe.
  • D. Walewice
    Walewice is a village in central Poland, historically notable as the birthplace of statesman and diplomat Alexandre Colonna-Walewski, the son of Napoleon Bonaparte and Countess Maria Walewska.
  • E. Dolina Chochołowska
    Dolina Chochołowska is the largest and one of the most scenic valleys in the Polish Tatra Mountains, known for its extensive hiking trails and spring crocus blooms.
  • 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_69a4934c753c81909b309027e48b9b3a completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4a591124c8190842e7ef18b064198 completed March 1, 2026, 8:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69a6891b6d908190823a9a09cef5c7da completed March 3, 2026, 7:09 a.m.
NEDg Description generation batch_69a68b72910081908792bc4760b0610a completed March 3, 2026, 7:19 a.m.
NED2 Entity disambiguation (via description) batch_69a6d634d6f08190a59ebda3bfe0d3db completed March 3, 2026, 12:38 p.m.
Created at: March 1, 2026, 7:37 p.m.