Triple
T21652985
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michaela |
E534386
|
entity |
| Predicate | hasVariant |
P455
|
FINISHED |
| Object | Mihaela |
—
|
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: Mihaela | Statement: [Michaela, hasVariant, Mihaela]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mihaela Context triple: [Michaela, hasVariant, Mihaela]
-
A.
Corina
Corina is a feminine given name used in various cultures, often considered a variant of names like Corine or Corinna.
-
B.
Catinca
Catinca is a Romanian actress best known for her acclaimed role as Alexandria in the fantasy film "The Fall" (2006).
-
C.
Maria Sursuvul
Maria Sursuvul was a Bulgarian noblewoman of the early medieval period, best known as the mother of Tsar Peter I of Bulgaria.
-
D.
Michela
chosen
Michela is a given name, commonly used in Italian- and Portuguese-speaking countries as a feminine form of Michael.
-
E.
Maria Voichița
Maria Voichița was a Moldavian princess and consort, best known as one of the wives of Stephen the Great, ruler of Moldavia in the late 15th century.
- 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_69e0c466aec88190ba39c7543dbc8ba2 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef591594a08190bf0ddd0a0c0922ba |
completed | April 27, 2026, 12:39 p.m. |
Created at: April 16, 2026, 6:36 p.m.