Triple
T16451919
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Regio IV Samnium |
E399571
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Minturnae |
E725085
|
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: Minturnae | Statement: [Regio IV Samnium, contains, Minturnae]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Minturnae Context triple: [Regio IV Samnium, contains, Minturnae]
-
A.
Minturnae
chosen
Minturnae was an ancient Roman town in Latium, Italy, situated along the Via Appia near the mouth of the Liris River and known for its strategic location and archaeological remains.
-
B.
Nomeny
Nomeny is a small historic commune in northeastern France, located in the Meurthe-et-Moselle department of the Grand Est region.
-
C.
Mendicino
Mendicino is a small town and comune in the Calabria region of southern Italy, known for its historic hilltop setting near the city of Cosenza.
-
D.
Verdesina
Verdesina is a small village in northern Italy’s Trentino region, situated within the alpine Val Rendena.
-
E.
Catonis
Catonis is a Latin cognomen most notably associated with the Roman statesman and moralist Cato and his family line.
- 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_69d87f2c6778819080fcfae53be8f12a |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e32ce19344819083d323077b742bc3 |
completed | April 18, 2026, 7:04 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a004598ec088190be80ad70e3f1357e |
completed | May 10, 2026, 8:45 a.m. |
Created at: April 10, 2026, 5:10 a.m.