Triple
T18029445
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Exar Kun |
E431346
|
entity |
| Predicate | enemy |
P4567
|
FINISHED |
| Object | Vodo-Siosk Baas |
—
|
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: Vodo-Siosk Baas | Statement: [Exar Kun, enemy, Vodo-Siosk Baas]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Vodo-Siosk Baas Context triple: [Exar Kun, enemy, Vodo-Siosk Baas]
-
A.
Vodo-Siosk Baas
chosen
Vodo-Siosk Baas is a revered Jedi Master from Star Wars Legends, known for training Exar Kun and playing a key role in the events leading up to the Great Sith War.
-
B.
Vabis
Vabis was a Swedish automotive and engineering company that later merged to form Scania-Vabis, a predecessor of the modern Scania AB.
-
C.
Kvasy
Kvasy is a village in western Ukraine’s Zakarpattia region, known as a starting point for hikes in the Carpathian Mountains and for its mineral springs.
-
D.
Baas
Baas is a Dutch surname most notably associated with contemporary designer Maarten Baas, known for his conceptual and often playful furniture and art pieces.
-
E.
The Vodi
The Vodi is a novel by British author John Braine, best known for its darkly psychological exploration of guilt, illness, and alienation in postwar England.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b9050fb48190890155145deb0a66 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4be347f6c8190b324fe74b7dc1764 |
completed | April 19, 2026, 11:36 a.m. |
Created at: April 10, 2026, 10:25 a.m.