Triple

T3806618
Position Surface form Disambiguated ID Type / Status
Subject Bulgarian royal family E93021 entity
Predicate residence P75 FINISHED
Object Vrana Palace
Vrana Palace is a historic royal estate near Sofia that served as the primary countryside residence of Bulgaria’s monarchs.
E389996 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: Vrana Palace | Statement: [Bulgarian royal family, residence, Vrana Palace]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Vrana Palace
Context triple: [Bulgarian royal family, residence, Vrana Palace]
  • A. Grassalkovich Palace
    Grassalkovich Palace is a historic rococo-style palace in Bratislava that serves as the official presidential residence of Slovakia.
  • B. Çırağan Palace
    Çırağan Palace is a historic Ottoman imperial palace on the Bosphorus in Istanbul, now a luxury hotel and event venue.
  • C. Cantacuzino Palace
    Cantacuzino Palace is a historic and ornate early 20th-century building in Bucharest, Romania, best known today as the George Enescu Museum.
  • D. Ehrenburg Palace
    Ehrenburg Palace is a historic Renaissance-style palace in Coburg, Germany, long associated with the ducal family of Saxe-Coburg and Gotha.
  • E. Strelna Palace
    Strelna Palace is an 18th-century imperial residence near Saint Petersburg, Russia, known for its Baroque architecture and association with the Russian royal family.
  • 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: Vrana Palace
Triple: [Bulgarian royal family, residence, Vrana Palace]
Generated description
Vrana Palace is a historic royal estate near Sofia that served as the primary countryside residence of Bulgaria’s monarchs.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Vrana Palace
Target entity description: Vrana Palace is a historic royal estate near Sofia that served as the primary countryside residence of Bulgaria’s monarchs.
  • A. Grassalkovich Palace
    Grassalkovich Palace is a historic rococo-style palace in Bratislava that serves as the official presidential residence of Slovakia.
  • B. Çırağan Palace
    Çırağan Palace is a historic Ottoman imperial palace on the Bosphorus in Istanbul, now a luxury hotel and event venue.
  • C. Cantacuzino Palace
    Cantacuzino Palace is a historic and ornate early 20th-century building in Bucharest, Romania, best known today as the George Enescu Museum.
  • D. Ehrenburg Palace
    Ehrenburg Palace is a historic Renaissance-style palace in Coburg, Germany, long associated with the ducal family of Saxe-Coburg and Gotha.
  • E. Strelna Palace
    Strelna Palace is an 18th-century imperial residence near Saint Petersburg, Russia, known for its Baroque architecture and association with the Russian royal family.
  • 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_69aed96a60088190ab1df8390fffc935 completed March 9, 2026, 2:30 p.m.
NER Named-entity recognition batch_69aee809c5c481909d5412cdd33b458d completed March 9, 2026, 3:32 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4fb2d7be48190a041e59b706751a4 completed March 14, 2026, 6:07 a.m.
NEDg Description generation batch_69b4fc463bf48190b604d478f2c3e477 completed March 14, 2026, 6:12 a.m.
NED2 Entity disambiguation (via description) batch_69b4fcb59c148190b2b574c787473896 completed March 14, 2026, 6:14 a.m.
Created at: March 9, 2026, 3:16 p.m.