Triple

T5970387
Position Surface form Disambiguated ID Type / Status
Subject Jovanka Broz E132856 entity
Predicate residence P75 FINISHED
Object Beli Dvor
Beli Dvor is a royal palace in Belgrade, Serbia, historically used as a residence by members of the Yugoslav and later Serbian leadership.
 E559874 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: Beli Dvor | Statement: [Jovanka Broz, residence, Beli Dvor]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Beli Dvor
Context triple: [Jovanka Broz, residence, Beli Dvor]
  • A. Ledovy Dvorets
    Ledovy Dvorets is a major indoor ice arena and multi-purpose sports and entertainment venue in Saint Petersburg, Russia.
  • B. Kozelets
    Kozelets is an urban-type settlement in northern Ukraine, historically known as a local administrative and trading center.
  • C. Blansko
    Blansko is a small industrial town in the South Moravian Region of the Czech Republic, known as a gateway to the Moravian Karst cave system.
  • D. Krasny Kut
    Krasny Kut is a small town in southwestern Russia known as an administrative and agricultural center within the Saratov region.
  • E. Vrana Palace
    Vrana Palace is a historic royal estate near Sofia that served as the primary countryside residence of Bulgaria’s monarchs.
  • 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: Beli Dvor
Triple: [Jovanka Broz, residence, Beli Dvor]
Generated description
Beli Dvor is a royal palace in Belgrade, Serbia, historically used as a residence by members of the Yugoslav and later Serbian leadership.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Beli Dvor
Target entity description: Beli Dvor is a royal palace in Belgrade, Serbia, historically used as a residence by members of the Yugoslav and later Serbian leadership.
  • A. Ledovy Dvorets
    Ledovy Dvorets is a major indoor ice arena and multi-purpose sports and entertainment venue in Saint Petersburg, Russia.
  • B. Kozelets
    Kozelets is an urban-type settlement in northern Ukraine, historically known as a local administrative and trading center.
  • C. Blansko
    Blansko is a small industrial town in the South Moravian Region of the Czech Republic, known as a gateway to the Moravian Karst cave system.
  • D. Krasny Kut
    Krasny Kut is a small town in southwestern Russia known as an administrative and agricultural center within the Saratov region.
  • E. Vrana Palace
    Vrana Palace is a historic royal estate near Sofia that served as the primary countryside residence of Bulgaria’s monarchs.
  • 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_69c0086deab081908550159ca23eec9b completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c03a4263e8819084e98e6c016c9532 completed March 22, 2026, 6:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0e40a67bc8190a57884f7c6aa1b9d completed March 23, 2026, 6:56 a.m.
NEDg Description generation batch_69c0f88f4e048190810351c4aebf363c completed March 23, 2026, 8:23 a.m.
NED2 Entity disambiguation (via description) batch_69c0f982c95c819081b2cf2c429c21bc completed March 23, 2026, 8:27 a.m.
Created at: March 22, 2026, 4:03 p.m.