Triple
T1703105
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gaius Marius |
E36809
|
entity |
| Predicate | birthPlace |
P1
|
FINISHED |
| Object | Arpinum |
E194569
|
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: Arpinum | Statement: [Gaius Marius, birthPlace, Arpinum]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Arpinum Context triple: [Gaius Marius, birthPlace, Arpinum]
-
A.
Arpinum
chosen
Arpinum is an ancient Italian town in Latium best known as the birthplace of the Roman statesman and orator Cicero.
-
B.
Clusium
Clusium was an important ancient Etruscan city, known for its strategic location in central Italy and its significant role in early Roman history.
-
C.
Velletri
Velletri is a historic town in the Lazio region of central Italy, known for its ancient Roman roots, wine production, and location in the Alban Hills southeast of Rome.
-
D.
Carpineto Romano
Carpineto Romano is a historic hill town in the Lazio region of central Italy, best known as the birthplace of Pope Leo XIII.
-
E.
Antium
Antium was an ancient coastal town in Latium, Italy, notable as a resort and birthplace of several Roman emperors, including Caligula and Nero.
- 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_69a88617439c819094ffb5d16a0f6307 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69aa62f0eb408190809d1f6496d38e0b |
completed | March 6, 2026, 5:15 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ada0ccf91881909f788d425f66d9eb |
completed | March 8, 2026, 4:16 p.m. |
Created at: March 4, 2026, 7:30 p.m.