Triple
T16093285
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mici |
E390414
|
entity |
| Predicate | shortFormOf |
P43
|
FINISHED |
| Object | Mária Harkányi |
E1194980
|
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: Mária Harkányi | Statement: [Mici, shortFormOf, Mária Harkányi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mária Harkányi Context triple: [Mici, shortFormOf, Mária Harkányi]
-
A.
Mária Harkányi
chosen
Mária Harkányi was a Hungarian individual known by the given name Mici, likely recognized in Hungarian cultural or social contexts.
-
B.
Klára Fülepp
Klára Fülepp is best known as the wife of József Antall, the first democratically elected Prime Minister of Hungary after the fall of communism.
-
C.
Jarmila Marton
Jarmila Marton was the wife of Hungarian-American film director Andrew Marton, known primarily in relation to his personal life.
-
D.
Józsefina Festetics
Józsefina Festetics was a Hungarian noblewoman from the influential Festetics family and the mother of statesman and reformer István Széchenyi.
-
E.
Hilda Péter
Hilda Péter is an actress best known for her role in the psychological horror film "Berberian Sound Studio."
- 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_69d87f198bc48190a8b7e53ca15b7ead |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e1858ed09881909bde122971d95753 |
completed | April 17, 2026, 12:57 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fff29da7008190aebeb35113e726ef |
completed | May 10, 2026, 2:51 a.m. |
Created at: April 10, 2026, 4:59 a.m.