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.