Triple
T19296539
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | István Kertész |
E482578
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Kertész |
—
|
NE NERFINISHED |
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: Kertész | Statement: [István Kertész, familyName, Kertész]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kertész Context triple: [István Kertész, familyName, Kertész]
-
A.
Kertész
chosen
Kertész is a Hungarian surname most notably borne by Nobel Prize–winning author Imre Kertész.
-
B.
Mihály Kertész
Mihály Kertész, better known as Michael Curtiz, was a Hungarian-American film director renowned for classics such as "Casablanca" and "The Adventures of Robin Hood."
-
C.
Laszlo Kovacs
László Kovács was a renowned Hungarian-American cinematographer celebrated for his influential work on numerous New Hollywood films, including classics like "Easy Rider" and "Five Easy Pieces."
-
D.
K. Sarneczky
K. Sarneczky is an astronomer known for discovering the trans-Neptunian object Varuna.
-
E.
Zsuzsa Cserháti
Zsuzsa Cserháti was a popular Hungarian pop and soul singer known for her powerful voice and emotive ballads, especially prominent from the 1970s onward.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e8cf61b0819096fe3e4107827c4e |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e5fc85e8988190a98bc291121f0153 |
completed | April 20, 2026, 10:14 a.m. |
Created at: April 10, 2026, 1:31 p.m.