Triple
T11204765
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Silistra |
E265131
|
entity |
| Predicate | wasRomanFortress |
P50573
|
FINISHED |
| Object | true |
—
|
LITERAL 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: true | Statement: [Silistra, wasRomanFortress, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasRomanFortress Context triple: [Silistra, wasRomanFortress, true]
-
A.
wasRomanFort
chosen
Indicates that the subject functioned as a Roman military fort at some point in time.
-
B.
wasRomanTown
Indicates that the subject entity functioned as a town or urban settlement during the period of the Roman Empire.
-
C.
wasRomanSettlementName
Indicates that the subject was the name used for a settlement during the Roman period.
-
D.
wasRomanProtectorate
Indicates that one political entity was under the protection and partial control of the Roman state as a protectorate.
-
E.
mainRomanSanctuary
Indicates that one entity serves as the primary Roman religious sanctuary or temple associated with another entity.
- 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_69d6aa9eb9248190b20211772621b4bc |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e8d355c481908fc3d555b596314d |
completed | April 9, 2026, 5:58 p.m. |
| PD | Predicate disambiguation | batch_69d75cf83464819087529d47d025d313 |
completed | April 9, 2026, 8:02 a.m. |
Created at: April 8, 2026, 9:30 p.m.