Triple
T2418635
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jules Schelvis |
E52365
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Jules Schelvis |
E52365
|
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: Jules Schelvis | Statement: [Jules Schelvis, name, Jules Schelvis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jules Schelvis Context triple: [Jules Schelvis, name, Jules Schelvis]
-
A.
Jules Schelvis
chosen
Jules Schelvis was a Dutch Jewish Holocaust survivor, historian, and author who became a leading expert and witness on the Sobibor extermination camp.
-
B.
Pierre De Geyter
Pierre De Geyter was a Belgian composer best known for writing the music to the socialist anthem "The Internationale."
-
C.
César De Paepe
César De Paepe was a prominent 19th-century Belgian socialist thinker and physician who played a leading role in the early international labor movement.
-
D.
Alexandre De Meyer
Alexandre De Meyer is a music producer known for his work on Kanye West’s influential album "808s & Heartbreak."
-
E.
Jan D'Alquen
Jan D'Alquen is a cinematographer best known for his work on the classic coming-of-age film "American Graffiti."
- 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_69ab495622948190bc6bc6e4cddaf645 |
completed | March 6, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69abc950516c8190989591673de6b1f7 |
completed | March 7, 2026, 6:44 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69aebf5397508190b755e522060041c0 |
completed | March 9, 2026, 12:38 p.m. |
Created at: March 6, 2026, 9:42 p.m.