Triple
T9487105
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | cohors II Raetorum |
E228788
|
entity |
| Predicate | stationedOn |
P88394
|
FINISHED |
| Object | Germanic frontier |
—
|
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: Germanic frontier | Statement: [cohors II Raetorum, stationedOn, Germanic frontier]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: stationedOn Context triple: [cohors II Raetorum, stationedOn, Germanic frontier]
-
A.
aircraftStationed
Indicates that an aircraft is based at, assigned to, or regularly located at a particular place or facility.
-
B.
headquartersStation
Indicates that a particular station serves as the main headquarters location for an organization or entity.
-
C.
countryStationed
Indicates that an entity is assigned, based, or deployed within the territory of a specified country.
-
D.
stationedInProvince
Indicates that an entity is assigned or based in a particular province as its location or area of operation.
-
E.
flagshipStationFor
Indicates that one station serves as the primary or leading representative station for a particular network, organization, or service.
- F. None of above. chosen
Provenance (4 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_69ca847424f081908180305555139f7a |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd8051303881909566126a2688e41c |
completed | April 1, 2026, 8:30 p.m. |
| PD | Predicate disambiguation | batch_69cca561e6b0819090aa795f3c3a2083 |
completed | April 1, 2026, 4:56 a.m. |
| PDg | Predicate description generation | batch_69cca89d0f0c8190b4528990fe708fca |
completed | April 1, 2026, 5:09 a.m. |
Created at: March 30, 2026, 7:55 p.m.