Triple

T11039052
Position Surface form Disambiguated ID Type / Status
Subject László Kovács E260960 entity
Predicate familyName P18 FINISHED
Object Kovács E163516 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: Kovács | Statement: [László Kovács, familyName, Kovács]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kovács
Context triple: [László Kovács, familyName, Kovács]
  • A. Kovács chosen
    Kovács is a common Hungarian surname equivalent to the English surname Smith, traditionally associated with the occupation of a blacksmith.
  • B. Várkonyi
    Várkonyi is a Hungarian surname most notably borne by the early 20th-century film and stage actor Victor Varconi.
  • C. Vadasz
    Vadasz is the surname of Leslie Vadasz, a Hungarian-American engineer and Intel founding member known for his contributions to semiconductor technology.
  • D. Jenő
    Jenő is the Hungarian given name of the renowned theoretical physicist and mathematician Wigner Jenő Pál, known in English as Eugene Wigner.
  • E. Kállay
    Kállay is a Hungarian surname most notably associated with Miklós Kállay, who served as Prime Minister of Hungary during World War II.
  • 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_69d6aa979bdc8190bf0e79104cc098c1 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d797fe93b081909d58bfd4b42715f0 completed April 9, 2026, 12:13 p.m.
NED1 Entity disambiguation (via context triple) batch_69e3a9d61b548190949f0dfbcb782064 completed April 18, 2026, 3:57 p.m.
Created at: April 8, 2026, 9:26 p.m.