Triple
T3958965
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Normans |
E85853
|
entity |
| Predicate | hasOrigin |
P26
|
FINISHED |
| Object | Vikings |
E78998
|
NE 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: Vikings | Statement: [Normans, hasOrigin, Vikings]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Vikings Context triple: [Normans, hasOrigin, Vikings]
-
A.
Vikings
The Vikings are the athletic teams representing Portland State University in NCAA Division I sports.
-
B.
Vikings
chosen
Vikings were seafaring Norse peoples from Scandinavia known for their raids, exploration, trade, and settlement across wide areas of Europe and the North Atlantic during the late eighth to early eleventh centuries.
-
C.
Vikings
The Vikings are the athletic teams representing Cleveland State University in NCAA Division I sports.
-
D.
Viking
"Viking" is a Russian historical epic film depicting the rise of Prince Vladimir and the Christianization of Kievan Rus.
-
E.
Viking
Viking is a prominent American publishing imprint known for releasing influential fiction and nonfiction titles, including many literary classics and bestsellers.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69aed93a96908190bcbdbfa718f155bd |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aef95ef8988190ba504cdfc217c4fa |
completed | March 9, 2026, 4:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b533b57ad08190972d385a133c73b8 |
completed | March 14, 2026, 10:08 a.m. |
Created at: March 9, 2026, 3:31 p.m.