Triple
T6954655
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mark |
E161211
|
entity |
| Predicate | hasVariant |
P455
|
FINISHED |
| Object | Marek |
E352681
|
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: Marek | Statement: [Mark, hasVariant, Marek]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marek Context triple: [Mark, hasVariant, Marek]
-
A.
Marek
chosen
Marek is a common given name in several Slavic countries, equivalent to the Latin name Marcus.
-
B.
Marek Belka
Marek Belka is a Polish economist and politician who served as Prime Minister of Poland and later as president of the National Bank of Poland.
-
C.
Feliks
Feliks is a given name, commonly used in Slavic and other European languages, that corresponds to the name Felix.
-
D.
Jacek
Jacek is a common Polish male given name, often associated with notable figures in Polish politics, arts, and academia.
-
E.
Husák
Husák is a Slovak surname most prominently associated with Gustáv Husák, the communist politician who served as president of Czechoslovakia during the normalization era.
- 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_69c68852a9a0819097797e31d492e273 |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6dace1a94819095311e4288f01784 |
completed | March 27, 2026, 7:30 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c75883f6888190a75515be49e7879e |
completed | March 28, 2026, 4:26 a.m. |
Created at: March 27, 2026, 2:29 p.m.