Triple
T36821180
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hispania Tarraconensis |
E909887
|
entity |
| Predicate | hadRomanRoad |
P47630
|
FINISHED |
| Object | Via Augusta |
—
|
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: Via Augusta | Statement: [Hispania Tarraconensis, hadRomanRoad, Via Augusta]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hadRomanRoad Context triple: [Hispania Tarraconensis, hadRomanRoad, Via Augusta]
-
A.
romanRoad
chosen
Indicates that one location is connected to another by a road constructed or used during the Roman period.
-
B.
romanRoadNetworkNode
Indicates that an entity functions as a node or junction point within a Roman road network, serving as a connection or intersection between Roman roads.
-
C.
wasRomanTown
Indicates that the subject entity functioned as a town or urban settlement during the period of the Roman Empire.
-
D.
hasRomanRemains
Indicates that the subject contains or is the location of physical remains or archaeological evidence from the Roman period.
-
E.
hillOfRome
Indicates that one entity is a hill that is located in or associated with the city of Rome.
- 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_69f76e7dd13c81908c60b05adb49eeb5 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f7ca989d50819095369c3d5af0fa2b |
completed | May 3, 2026, 10:22 p.m. |
| PD | Predicate disambiguation | batch_69f7c89b528c8190bf80b230fc7c7108 |
completed | May 3, 2026, 10:13 p.m. |
Created at: May 3, 2026, 4:13 p.m.