Triple

T1930193
Position Surface form Disambiguated ID Type / Status
Subject Kingdom of Hungary E40926 entity
Predicate hasPart P35 FINISHED
Object Transylvania E72198 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: Transylvania | Statement: [Kingdom of Hungary, hasPart, Transylvania]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Transylvania
Context triple: [Kingdom of Hungary, hasPart, Transylvania]
  • A. Transylvania chosen
    Transylvania is a historical region in central Romania, famed for its medieval castles, fortified churches, and association with the Dracula legend.
  • B. Wallachia
    Wallachia is a historical region in southern Romania that played a central role in medieval Eastern European politics and is famously associated with figures like Vlad the Impaler.
  • C. Bukovina
    Bukovina is a historical region in Eastern Europe, now divided between Romania and Ukraine, known for its multicultural heritage and once forming part of the Austro-Hungarian Empire.
  • D. Romania
    Romania is a southeastern European country known for its role in World War II, its Carpathian mountain landscapes, and its historical regions such as Transylvania.
  • E. Maramureș region
    The Maramureș region is a historic area in northern Romania renowned for its well-preserved rural traditions, wooden churches, and distinctive folk culture.
  • 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_69a8864711648190b07bed24ed76258e completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69abb266dcb4819090be83556615d0db completed March 7, 2026, 5:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69adf3ed31448190a2e5d088ab5886b8 completed March 8, 2026, 10:10 p.m.
Created at: March 4, 2026, 7:35 p.m.