Triple
T23649958
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | conventus of Rotomagus |
E584139
|
entity |
| Predicate | centerCityAncientName |
P117012
|
FINISHED |
| Object | Rotomagus |
—
|
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: Rotomagus | Statement: [conventus of Rotomagus, centerCityAncientName, Rotomagus]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: centerCityAncientName Context triple: [conventus of Rotomagus, centerCityAncientName, Rotomagus]
-
A.
ancientNameOf
Indicates that one entity is the historical or ancient name by which the other entity was formerly known.
-
B.
ancientCity
Indicates that the subject is a historically old or long-established city, typically originating from ancient times.
-
C.
ancientNameOfServedSettlement
chosen
Indicates that the object is an earlier or historical name by which the settlement served by the subject was known.
-
D.
majorAncientCity
Indicates that a location functioned as a principal or highly significant city during ancient historical periods.
-
E.
ancientDistrictOf
Indicates that one entity is an ancient or historical district that forms part of, or is located within, 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_69e248fefafc81909656921192f30e80 |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b2885b408190a43dfed93309a4d6 |
completed | April 29, 2026, 7:26 a.m. |
| PD | Predicate disambiguation | batch_69f118d7903c8190bb590a71771e93af |
completed | April 28, 2026, 8:30 p.m. |
Created at: April 17, 2026, 6:49 p.m.