Triple
T18401144
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gettysburg (1993 film) |
E449997
|
entity |
| Predicate | cinematographer |
P1953
|
FINISHED |
| Object | Kees Van Oostrum |
—
|
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: Kees Van Oostrum | Statement: [Gettysburg (1993 film), cinematographer, Kees Van Oostrum]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kees Van Oostrum Context triple: [Gettysburg (1993 film), cinematographer, Kees Van Oostrum]
-
A.
Kees Van Oostrum
chosen
Kees Van Oostrum is a Dutch-born cinematographer known for his work in film and television and for serving as president of the American Society of Cinematographers.
-
B.
Cees Roozemond
Cees Roozemond is a Dutch football executive known for serving as the chairman of Eredivisie club SC Heerenveen.
-
C.
Frank van der Meijden
Frank van der Meijden is a Dutch local politician who serves as the mayor of the municipality of Laarbeek in the Netherlands.
-
D.
Johan de Jonge
Johan de Jonge is a person notable enough to be recognized as a distinguished bearer of the surname "de Jonge."
-
E.
Dennis van Aarssen
Dennis van Aarssen is a Dutch jazz and pop singer who gained national fame after winning the talent show The Voice of Holland.
- 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_69d8b9fab8a8819086a9ddc0871715e0 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e5195185b08190bd3b5471cdc047b0 |
completed | April 19, 2026, 6:05 p.m. |
Created at: April 10, 2026, 10:46 a.m.