Triple
T12877264
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Showgirls |
E308000
|
entity |
| Predicate | director |
P255
|
FINISHED |
| Object | Paul Verhoeven |
E329582
|
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: Paul Verhoeven | Statement: [Showgirls, director, Paul Verhoeven]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Paul Verhoeven Context triple: [Showgirls, director, Paul Verhoeven]
-
A.
Paul Verhoeven
chosen
Paul Verhoeven is a Dutch filmmaker known for his provocative, violent, and satirical films such as RoboCop, Total Recall, and Starship Troopers.
-
B.
Bob Noorda
Bob Noorda was a renowned Dutch graphic designer celebrated for his pioneering work in modernist corporate and transportation visual identity systems.
-
C.
Rolf Weitz
Rolf Weitz is an individual notable enough to be specifically cited as a bearer of the surname Weitz.
-
D.
Fred Dekker
Fred Dekker is an American filmmaker and screenwriter best known for cult horror and sci-fi films such as "Night of the Creeps," "The Monster Squad," and his collaborations with Shane Black.
-
E.
Jan de Bont
Jan de Bont is a Dutch cinematographer and film director best known for shooting visually dynamic action films and directing hits like Speed and Twister.
- 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.