Triple

T10990377
Position Surface form Disambiguated ID Type / Status
Subject Government of Croatia E259739 entity
Predicate seat P75 FINISHED
Object Banski dvori E465297 NE FINISHED

How this triple was built (2 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: Banski dvori | Statement: [Government of Croatia, seat, Banski dvori]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Banski dvori
Context triple: [Government of Croatia, seat, Banski dvori]
  • A. Banski dvori chosen
    Banski dvori is a historic Baroque palace in Zagreb that serves as the official seat of the Croatian government and the office of the Prime Minister.
  • B. 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.
  • C. Cankarjeva cesta
    Cankarjeva cesta is a central street in Ljubljana, Slovenia, known for hosting important cultural institutions and landmarks.
  • D. Dušan's Code
    Dušan's Code is a 14th-century Serbian legal codex issued by Emperor Stefan Dušan that systematized medieval Serbian law and governance.
  • E. Ledovy Dvorets
    Ledovy Dvorets is a major indoor ice arena and multi-purpose sports and entertainment venue in Saint Petersburg, Russia.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d6aa8a6a548190a750f944ccdc8064 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d787b8d7088190b7d6b63c3bac4ad1 completed April 9, 2026, 11:04 a.m.
NED1 Entity disambiguation (via context triple) batch_69e34504ebec8190a78e4795765b0c24 completed April 18, 2026, 8:47 a.m.
Created at: April 8, 2026, 9:24 p.m.