Triple
T8692353
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tullia Ciceronis |
E206321
|
entity |
| Predicate | mother |
P120
|
FINISHED |
| Object | Terentia |
E200340
|
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: Terentia | Statement: [Tullia Ciceronis, mother, Terentia]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Terentia Context triple: [Tullia Ciceronis, mother, Terentia]
-
A.
Terentia
chosen
Terentia was the first wife of the Roman orator and statesman Cicero, known for her wealth, social influence, and involvement in his political and personal affairs.
-
B.
Terentius
Terentius is an ancient Roman family name (nomen) that gave rise to the later surname Terence.
-
C.
Publilia
Publilia was the second wife of the Roman orator and statesman Marcus Tullius Cicero, whom he married after divorcing Terentia.
-
D.
Florus
Florus was a Roman historian and rhetorician best known for his epitome of Roman history, which includes an account of the Third Servile War.
-
E.
Caecilius
Caecilius is the family name of a prominent ancient Roman gens that included influential politicians and military leaders such as Quintus Caecilius Metellus Numidicus.
- 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_69ca835481fc819084e33d3bc883bfa6 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc5825385081908dee42cba8e98392 |
completed | March 31, 2026, 11:26 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cef3ea2ba08190b8046e703ba7d2d8 |
completed | April 2, 2026, 10:55 p.m. |
Created at: March 30, 2026, 6:33 p.m.