Triple

T19097146
Position Surface form Disambiguated ID Type / Status
Subject Nivy E467434 entity
Predicate hasStreet P959 FINISHED
Object Karadžičova
Karadžičova is a major street in the Nivy district of Bratislava, Slovakia, known for its office buildings and heavy traffic.
 E1359405 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: Karadžičova | Statement: [Nivy, hasStreet, Karadžičova]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Karadžičova
Context triple: [Nivy, hasStreet, Karadžičova]
  • A. Krajišnik
    Krajišnik is a village located within the Temerin municipality in the Vojvodina region of northern Serbia.
  • B. Kardelj
    Kardelj is a Slovene surname most prominently associated with Edvard Kardelj, a leading Yugoslav communist theorist and politician.
  • C. Kruščić
    Kruščić is a village in northern Serbia that forms part of the Kula municipality in the autonomous province of Vojvodina.
  • D. Tršić
    Tršić is a Serbian village best known as the birthplace of the renowned language reformer and folklorist Vuk Karadžić.
  • E. Velenjak
    Velenjak is an affluent residential and cultural neighborhood in northern Tehran, known for its proximity to the Alborz mountains and several major universities.
  • 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: Karadžičova
Triple: [Nivy, hasStreet, Karadžičova]
Generated description
Karadžičova is a major street in the Nivy district of Bratislava, Slovakia, known for its office buildings and heavy traffic.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Karadžičova
Target entity description: Karadžičova is a major street in the Nivy district of Bratislava, Slovakia, known for its office buildings and heavy traffic.
  • A. Krajišnik
    Krajišnik is a village located within the Temerin municipality in the Vojvodina region of northern Serbia.
  • B. Kardelj
    Kardelj is a Slovene surname most prominently associated with Edvard Kardelj, a leading Yugoslav communist theorist and politician.
  • C. Kruščić
    Kruščić is a village in northern Serbia that forms part of the Kula municipality in the autonomous province of Vojvodina.
  • D. Tršić
    Tršić is a Serbian village best known as the birthplace of the renowned language reformer and folklorist Vuk Karadžić.
  • E. Velenjak
    Velenjak is an affluent residential and cultural neighborhood in northern Tehran, known for its proximity to the Alborz mountains and several major universities.
  • 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_69d8dd05ac4c8190b1967d8f97f3fb2f completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5e369aeac81908913c21f4c234c8e completed April 20, 2026, 8:27 a.m.
NED1 Entity disambiguation (via context triple) batch_6a05e669d35c819099e2152231197c27 completed May 14, 2026, 3:12 p.m.
NEDg Description generation batch_6a05e87086048190bb33e123a75d6b56 completed May 14, 2026, 3:21 p.m.
NED2 Entity disambiguation (via description) batch_6a05e8f73de48190831b72700709055e completed May 14, 2026, 3:23 p.m.
Created at: April 10, 2026, 12:04 p.m.