Triple
T19779950
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mateusz |
E475103
|
entity |
| Predicate | hasVariant |
P455
|
FINISHED |
| Object | Matija |
—
|
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: Matija | Statement: [Mateusz, hasVariant, Matija]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Matija Context triple: [Mateusz, hasVariant, Matija]
-
A.
Matija
chosen
Matija is a South Slavic given name, equivalent to the English name Matthew.
-
B.
Danijel
Danijel is the central male protagonist in the war drama film "In the Land of Blood and Honey," which explores a complex relationship set against the backdrop of the Bosnian War.
-
C.
Luka
Luka is a central character in Maxim Gorky's play "The Lower Depths," known as a compassionate wanderer whose comforting lies and philosophical outlook profoundly affect the other destitute inhabitants of the shelter.
-
D.
Luka
"Luka" is a 1987 folk-pop song by Suzanne Vega that poignantly addresses the subject of child abuse from a child's perspective.
-
E.
Luka
Luka is the young protagonist of Salman Rushdie’s fantasy novel "Luka and the Fire of Life," who embarks on a magical quest to save his father.
- 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_69d8e51a43a08190956bc6df13c91a77 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e65382ff308190832800dd60675f7a |
completed | April 20, 2026, 4:25 p.m. |
Created at: April 10, 2026, 1:49 p.m.