Triple
T12877284
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Showgirls |
E308000
|
entity |
| Predicate | cinematographyBy |
P1953
|
FINISHED |
| Object | Jost Vacano |
E405988
|
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: Jost Vacano | Statement: [Showgirls, cinematographyBy, Jost Vacano]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jost Vacano Context triple: [Showgirls, cinematographyBy, Jost Vacano]
-
A.
Jost Vacano
chosen
Jost Vacano is a German cinematographer renowned for his dynamic, technically innovative work on films such as "Das Boot," "RoboCop," and other major international productions.
-
B.
Nikolaus Zmeskall
Nikolaus Zmeskall was an Austrian civil servant, amateur cellist, and close friend of Ludwig van Beethoven who supported and inspired the composer’s chamber music activities.
-
C.
Bruno von Mudra
Bruno von Mudra was a German general of World War I known for his senior command roles on the Western Front.
-
D.
Raimundus
Raimundus is a Latinized given name historically used across medieval Europe, often associated with various saints, scholars, and nobles.
-
E.
Valter
Valter is a masculine given name used in various European countries, generally equivalent to the English name Walter.
- 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_69d7bdf69bc48190af6c2621f28ca351 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d970fa8474819086a8af3c90f3ca84 |
completed | April 10, 2026, 9:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f69bb83bac8190838f7537b806317c |
completed | May 3, 2026, 12:50 a.m. |
Created at: April 9, 2026, 5:38 p.m.