Triple
T29365488
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Byzantine Varangian Guard |
E744703
|
entity |
| Predicate | primaryRecruitmentRegion |
P14194
|
FINISHED |
| Object | Scandinavia |
—
|
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: Scandinavia | Statement: [Byzantine Varangian Guard, primaryRecruitmentRegion, Scandinavia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryRecruitmentRegion Context triple: [Byzantine Varangian Guard, primaryRecruitmentRegion, Scandinavia]
-
A.
laterRecruitmentRegion
Indicates that one entity’s recruitment occurred in a region that was involved at a later stage or phase compared to another recruitment region.
-
B.
primaryRegionOfPopularity
Indicates the geographic region where something is most widely used, favored, or popular compared to other regions.
-
C.
region1
Indicates that one entity is the first or primary region associated with, containing, or encompassing another entity.
-
D.
traditionalRegionOfResidence
chosen
Indicates the customary or historically established geographic region where an entity (typically a person or group) resides or is considered to be from.
-
E.
campaignRegion
Indicates the geographic area or territory in which a campaign is conducted or targeted.
- 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_69f0a79aee588190b490f19d93c6e52d |
completed | April 28, 2026, 12:27 p.m. |
| NER | Named-entity recognition | batch_6a011e5a419081908d06a07b395ebd97 |
completed | May 11, 2026, 12:10 a.m. |
| PD | Predicate disambiguation | batch_6a011de119048190b27d361cffabc228 |
completed | May 11, 2026, 12:08 a.m. |
Created at: April 28, 2026, 2:22 p.m.