Triple
T6954677
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mark |
E161211
|
entity |
| Predicate | hasCognate |
P2525
|
FINISHED |
| Object | Marcos |
E352679
|
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: Marcos | Statement: [Mark, hasCognate, Marcos]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marcos Context triple: [Mark, hasCognate, Marcos]
-
A.
Marcos
chosen
Marcos is a masculine given name, commonly used in Spanish- and Portuguese-speaking countries, that derives from the Latin name Marcus.
-
B.
Teodoro
Teodoro is a given name, commonly used in Romance-language countries, that corresponds to the English name Theodore.
-
C.
Juan Vicente
Juan Vicente is a Venezuelan military leader and politician of the early 19th century, best known as the father of independence hero Simón Bolívar.
-
D.
Augusto Vargas Alzamora
Augusto Vargas Alzamora was a Peruvian Cardinal of the Roman Catholic Church who served as Archbishop of Lima and was known for his outspoken defense of human rights and democracy.
-
E.
Mariano
Mariano is a masculine given name of Spanish and Portuguese origin, commonly used in various Spanish-speaking and Latin cultures.
- 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.