Triple
T756675
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Illyricum |
E15571
|
entity |
| Predicate | capital |
P234
|
FINISHED |
| Object | Sirmium |
E36825
|
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: Sirmium | Statement: [Illyricum, capital, Sirmium]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sirmium Context triple: [Illyricum, capital, Sirmium]
-
A.
Sirmium
chosen
Sirmium was an important ancient Roman city in the province of Pannonia, serving as a major military, administrative, and imperial center in the late Roman Empire.
-
B.
Salona
Salona was an important ancient Roman city on the Adriatic coast, serving as the chief urban center of the province of Dalmatia in present-day Croatia.
-
C.
Aquincum
Aquincum was an important ancient Roman military and civilian settlement located in what is now northern Budapest, Hungary.
-
D.
Naissus
Naissus was an important ancient Roman city in the province of Moesia, located at the site of modern-day Niš in Serbia.
-
E.
Argentoratum
Argentoratum is the ancient Roman military camp and settlement that later developed into the modern city of Strasbourg in northeastern France.
- 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_69a493599a0081908da65f3407af1ef2 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a66ab4608190afcd81e6606c5116 |
completed | March 1, 2026, 8:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a66673d6288190bb6a68c6c376016e |
completed | March 3, 2026, 4:41 a.m. |
Created at: March 1, 2026, 7:37 p.m.