Triple
T32362216
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cibalae |
E826894
|
entity |
| Predicate | hadRomanRoadConnectionTo |
P47630
|
FINISHED |
| Object | Sirmium |
—
|
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: Sirmium | Statement: [Cibalae, hadRomanRoadConnectionTo, Sirmium]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hadRomanRoadConnectionTo Context triple: [Cibalae, hadRomanRoadConnectionTo, Sirmium]
-
A.
romanRoad
chosen
Indicates that one location is connected to another by a road constructed or used during the Roman period.
-
B.
wasRomanTown
Indicates that the subject entity functioned as a town or urban settlement during the period of the Roman Empire.
-
C.
transportRouteInAntiquity
Indicates that there existed a transportation route between entities during ancient or classical historical periods.
-
D.
romanFortAssociatedWith
Indicates that there is a relationship of historical, functional, or spatial connection between a Roman fort and another entity.
-
E.
hasRomanRemains
Indicates that the subject contains or is the location of physical remains or archaeological evidence from the Roman period.
- F. None of above.
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_69f34915a2588190bb3178f5ec2f48f4 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6be9866448190b9225dd383e52ec8 |
completed | May 3, 2026, 3:18 a.m. |
| PD | Predicate disambiguation | batch_69f6ba6cef208190bc5cd43d96127004 |
completed | May 3, 2026, 3:01 a.m. |
Created at: May 1, 2026, 12:49 a.m.