Triple

T10443467
Position Surface form Disambiguated ID Type / Status
Subject Konstal 105Na E246225 entity
Predicate predecessor P97 FINISHED
Object Konstal 105N
The Konstal 105N is a Polish high-floor tram model introduced in the 1970s, widely used in many cities across Poland as a standard single-section streetcar.
 E864114 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: Konstal 105N | Statement: [Konstal 105Na, predecessor, Konstal 105N]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Konstal 105N
Context triple: [Konstal 105Na, predecessor, Konstal 105N]
  • A. Konstal 105Na tram
    The Konstal 105Na tram is a widely used Polish high-floor tram model introduced in the late 20th century and operated in many cities across Poland.
  • B. Contrex
    Contrex is a French mineral water brand known for its high mineral content and association with health and slimming.
  • C. Bondo
    Bondo is a town in western Kenya’s Nyanza region, known as an administrative and commercial center near Lake Victoria.
  • D. Borregaard
    Borregaard is a Norwegian biorefinery company that produces advanced and sustainable bio-based chemicals and materials from wood.
  • E. Aluminium Konin
    Aluminium Konin is a Polish football club known for competing in the lower tiers of the national league system.
  • 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: Konstal 105N
Triple: [Konstal 105Na, predecessor, Konstal 105N]
Generated description
The Konstal 105N is a Polish high-floor tram model introduced in the 1970s, widely used in many cities across Poland as a standard single-section streetcar.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Konstal 105N
Target entity description: The Konstal 105N is a Polish high-floor tram model introduced in the 1970s, widely used in many cities across Poland as a standard single-section streetcar.
  • A. Konstal 105Na tram
    The Konstal 105Na tram is a widely used Polish high-floor tram model introduced in the late 20th century and operated in many cities across Poland.
  • B. Contrex
    Contrex is a French mineral water brand known for its high mineral content and association with health and slimming.
  • C. Bondo
    Bondo is a town in western Kenya’s Nyanza region, known as an administrative and commercial center near Lake Victoria.
  • D. Borregaard
    Borregaard is a Norwegian biorefinery company that produces advanced and sustainable bio-based chemicals and materials from wood.
  • E. Aluminium Konin
    Aluminium Konin is a Polish football club known for competing in the lower tiers of the national league system.
  • 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_69d381c04fe08190957c26c526a3b05a completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4fdbd731c819084dfff83b4481ae8 completed April 7, 2026, 12:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69d87ee0c2208190ae8d51a2a89a2586 completed April 10, 2026, 4:38 a.m.
NEDg Description generation batch_69d886c3fdcc8190a67a7f7788b8a2e8 completed April 10, 2026, 5:12 a.m.
NED2 Entity disambiguation (via description) batch_69d88dc15ab481909011c5de93bbab14 completed April 10, 2026, 5:42 a.m.
Created at: April 6, 2026, 12:15 p.m.