Triple
T8941772
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alexander Dovzhenko |
E212917
|
entity |
| Predicate | employer |
P7
|
FINISHED |
| Object | VUFKU |
E747554
|
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: VUFKU | Statement: [Alexander Dovzhenko, employer, VUFKU]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: VUFKU Context triple: [Alexander Dovzhenko, employer, VUFKU]
-
A.
VUFKU
chosen
VUFKU was a pioneering Soviet Ukrainian film studio of the 1920s known for producing innovative avant-garde and documentary cinema.
-
B.
GUF
GUF is the three-letter ISO 3166-1 alpha-3 country code assigned to French Guiana.
-
C.
FÜ
FÜ is the vehicle registration code used on license plates for the city of Fürth in Bavaria, Germany.
-
D.
Kuuvak
Kuuvak is the traditional Indigenous name, used by local Iñupiat peoples, for the river known in English as the Kobuk River in northwestern Alaska.
-
E.
Varekai
Varekai is a Cirque du Soleil touring circus production known for its fantastical forest setting, acrobatic performances, and imaginative storytelling.
- 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_69ca839694c88190b324ffeb43d23b08 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc66b9c14c8190b80c3df0cdba2747 |
completed | April 1, 2026, 12:28 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfc1f418708190b1272209f61e3a51 |
completed | April 3, 2026, 1:34 p.m. |
Created at: March 30, 2026, 6:58 p.m.