Triple
T21993528
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Black Book |
E543146
|
entity |
| Predicate | editor |
P1954
|
FINISHED |
| Object | Job ter Burg |
—
|
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: Job ter Burg | Statement: [Black Book, editor, Job ter Burg]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Job ter Burg Context triple: [Black Book, editor, Job ter Burg]
-
A.
Job ter Burg
chosen
Job ter Burg is a Dutch film editor known for his work on numerous acclaimed international films.
-
B.
Woerdense Verlaat
Woerdense Verlaat is a small village in the Dutch province of South Holland, known for its rural character and location near waterways and polders.
-
C.
De Dokwerker
De Dokwerker is a bronze statue in Amsterdam commemorating the February Strike of 1941 and symbolizing resistance against Nazi persecution.
-
D.
The Dutchman
"The Dutchman" is a poignant folk ballad, popularized by Irish singer Liam Clancy, that tells the story of an elderly Dutch man and his devoted wife coping with aging and memory loss.
-
E.
Jeroentje
Jeroentje is a Dutch diminutive form of the given name Jeroen, typically used as an affectionate or informal nickname.
- 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_69e11e2c814c8190837d072789000486 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f1270f77fc8190aadcc02760d65ac0 |
completed | April 28, 2026, 9:30 p.m. |
Created at: April 16, 2026, 8:17 p.m.