Triple
T2664572
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John |
E55602
|
entity |
| Predicate | hasVariant |
P455
|
FINISHED |
| Object | Ioan |
E208142
|
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: Ioan | Statement: [John, hasVariant, Ioan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ioan Context triple: [John, hasVariant, Ioan]
-
A.
Ioan
chosen
Ioan is a given name, commonly used in Romanian and other Eastern European languages, that corresponds to the English name John.
-
B.
Petrus
Petrus is the Latin form of the name Peter, historically used in religious and classical contexts and serving as the root for various European given names.
-
C.
Cornelius
Cornelius is the given first name of Connie Mack, the legendary early 20th-century Major League Baseball manager and team owner.
-
D.
Cornelius
Cornelius is the ancient Roman gens (clan) to which the dictator Lucius Cornelius Sulla belonged.
-
E.
Gregory
Gregory is a masculine given name of Greek origin, historically associated with figures such as the American actor Gregory Peck.
- 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_69ab49e54de48190be708cd1cf8be073 |
completed | March 6, 2026, 9:40 p.m. |
| NER | Named-entity recognition | batch_69abd96dba44819085c3e651afba7806 |
completed | March 7, 2026, 7:53 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69af98dc36d8819086fc739c324f0761 |
completed | March 10, 2026, 4:06 a.m. |
Created at: March 6, 2026, 9:54 p.m.