Triple
T21964344
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marcus Atilius Regulus |
E542418
|
entity |
| Predicate | praenomen |
P7966
|
FINISHED |
| Object | Marcus |
—
|
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: Marcus | Statement: [Marcus Atilius Regulus, praenomen, Marcus]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marcus Context triple: [Marcus Atilius Regulus, praenomen, Marcus]
-
A.
Marcus
chosen
Marcus is a masculine given name of ancient Roman origin that has been widely used across many cultures and historical periods.
-
B.
Marco
Marco is the lightweight window manager used by the MATE desktop environment, designed as a continuation of GNOME 2’s Metacity.
-
C.
Marco
Marco is a masculine given name of Latin origin, commonly used in Italian, Spanish, and Portuguese-speaking countries.
-
D.
Marco
Marco is the costumed bison mascot of North Dakota State University’s athletic teams.
-
E.
Marco
Marco is the imaginative young boy and narrator in Dr. Seuss’s children’s book *And to Think That I Saw It on Mulberry Street*, known for wildly embellishing an ordinary walk home.
- 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_69e0c47fab1081908dc74a6545dbb051 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f12459e1848190aa8d4ccc97f434b8 |
completed | April 28, 2026, 9:19 p.m. |
Created at: April 16, 2026, 8:01 p.m.