Triple

T7053976
Position Surface form Disambiguated ID Type / Status
Subject Mihály Károlyi E164038 entity
Predicate name P16 FINISHED
Object Mihály Károlyi E164038 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: Mihály Károlyi | Statement: [Mihály Károlyi, name, Mihály Károlyi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mihály Károlyi
Context triple: [Mihály Károlyi, name, Mihály Károlyi]
  • A. Mihály Károlyi chosen
    Mihály Károlyi was a Hungarian politician and aristocrat who led the country during the transition from the Austro-Hungarian Empire to an independent republic after World War I.
  • B. Pál Teleki
    Pál Teleki was a Hungarian geographer and politician who twice served as Prime Minister of Hungary in the interwar period and early years of World War II.
  • C. Miklós Ybl
    Miklós Ybl was a prominent 19th-century Hungarian architect renowned for his influential role in shaping Budapest’s historic cityscape.
  • D. Frigyes Feszl
    Frigyes Feszl was a 19th-century Hungarian architect best known for his role in developing the Romantic and Moorish Revival architectural styles in Hungary.
  • E. Zala György
    Zala György was a Hungarian sculptor best known for his monumental public statues and memorials in Budapest at the turn of the 20th century.
  • 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_69c68861678881909961ddf4d779f750 completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6e265ea348190a9bd3807c0d605d8 completed March 27, 2026, 8:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7944535bc819086b7648d95b81e37 completed March 28, 2026, 8:41 a.m.
Created at: March 27, 2026, 2:37 p.m.