Triple
T14357820
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Károly Grósz |
E356015
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Grósz |
E356015
|
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: Grósz | Statement: [Károly Grósz, familyName, Grósz]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Grósz Context triple: [Károly Grósz, familyName, Grósz]
-
A.
Grósz
chosen
Grósz is a Hungarian surname most notably borne by Károly Grósz, a late-20th-century Hungarian communist politician and former Prime Minister.
-
B.
Gietrzwałd
Gietrzwałd is a village in northern Poland known as a Catholic pilgrimage site due to reported Marian apparitions in 1877.
-
C.
Witos
Witos is a Polish surname most notably borne by Wincenty Witos, a prominent early 20th-century Polish politician and three-time Prime Minister.
-
D.
Grześ
Grześ is a popular Tatra mountain peak in Poland, often visited as a scenic hiking destination offering views over the Chochołowska Valley and surrounding ranges.
-
E.
Graditz
Graditz is a locality in Germany known historically as the place where Charles Augustus, Grand Duke of Saxe-Weimar-Eisenach, died.
- 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_69d82790a7e08190877e2d349b2e8d8e |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de8f52ca7881908704eef20228aed3 |
completed | April 14, 2026, 7:02 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd4c473fa48190866ab946971e971c |
completed | May 8, 2026, 2:36 a.m. |
Created at: April 10, 2026, 1:15 a.m.