Triple
T15999960
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Skies of Arcadia |
E388067
|
entity |
| Predicate | mainCharacter |
P1183
|
FINISHED |
| Object | Vyse |
E1189336
|
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: Vyse | Statement: [Skies of Arcadia, mainCharacter, Vyse]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Vyse Context triple: [Skies of Arcadia, mainCharacter, Vyse]
-
A.
Vyse
Vyse is a surname most notably associated with British Egyptologist and army officer Richard William Howard Vyse, known for his controversial excavations at the Pyramids of Giza in the 19th century.
-
B.
Vyse
chosen
Vyse is the adventurous young sky pirate and main hero of the role-playing game Skies of Arcadia.
-
C.
Vyara
Vyara is a town in the Tapi district of South Gujarat, India, known as an important regional center for trade and administration.
-
D.
Vaneese
Vaneese is a female given name most notably borne by American singer, songwriter, and producer Vaneese Thomas.
-
E.
Vuze
Vuze is a feature-rich BitTorrent client known for its advanced download management, media playback, and integrated search capabilities.
- 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_69d86daa562c81908aacc179c0fe8fb5 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e1578a0adc819097c6a23514182173 |
completed | April 16, 2026, 9:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffdbca65a4819090109589dba7f7a9 |
completed | May 10, 2026, 1:13 a.m. |
Created at: April 10, 2026, 4:55 a.m.