Triple
T6954674
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mark |
E161211
|
entity |
| Predicate | hasCognate |
P2525
|
FINISHED |
| Object | Marko |
E352680
|
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: Marko | Statement: [Mark, hasCognate, Marko]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marko Context triple: [Mark, hasCognate, Marko]
-
A.
Marko
chosen
Marko is a masculine given name, commonly used in Slavic and other European cultures, that is cognate with the name Marcus.
-
B.
Marko Ramius
Marko Ramius is a highly skilled Soviet submarine captain who masterminds a risky defection to the West in Tom Clancy’s techno-thriller "The Hunt for Red October."
-
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 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.
-
E.
Dragomir
Dragomir is a Swedish actor and former criminal best known internationally for his role in the film "Easy Money" and appearances in action movies and TV series.
- 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.