Triple

T8847426
Position Surface form Disambiguated ID Type / Status
Subject Katalin Rényi E210540 entity
Predicate givenName P17 FINISHED
Object Katalin E232828 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: Katalin | Statement: [Katalin Rényi, givenName, Katalin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Katalin
Context triple: [Katalin Rényi, givenName, Katalin]
  • A. Katalin chosen
    Katalin is a Hungarian given name most prominently associated with biochemist Katalin Karikó, a pioneer of mRNA technology used in COVID-19 vaccines.
  • B. Mária
    Mária is the Hungarian and Slovak form of the given name Mary, commonly used in Central and Eastern Europe.
  • C. Terézia
    Terézia is the given name of the Hungarian-born German writer and translator Terézia Mora, known for her award-winning novels and screenplays.
  • D. Erzsébet Hunyadvári
    Erzsébet Hunyadvári was the wife of legendary Hungarian footballer Ferenc Puskás and a long-time companion throughout his playing and coaching career.
  • E. Mici Mária (Augusta Maria) Harkányi
    Mici Mária (Augusta Maria) Harkányi was the wife of Hungarian-American physicist Edward Teller, known for supporting him throughout his scientific and political career.
  • 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_69ca838967bc8190b46c3c80a2887ea4 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc60a9194c8190bdfefc55a8fb29a3 completed April 1, 2026, 12:02 a.m.
NED1 Entity disambiguation (via context triple) batch_69cf89bd3ef48190a6a2efff18db4dbd completed April 3, 2026, 9:34 a.m.
Created at: March 30, 2026, 6:49 p.m.