Triple
T20864720
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Donald Martin |
E513722
|
entity |
| Predicate | createdBy |
P806
|
FINISHED |
| Object | Georges Simenon |
—
|
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: Georges Simenon | Statement: [Donald Martin, createdBy, Georges Simenon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Georges Simenon Context triple: [Donald Martin, createdBy, Georges Simenon]
-
A.
Georges Simenon
chosen
Georges Simenon was a prolific Belgian writer best known for creating the fictional detective Jules Maigret and for his numerous psychological novels.
-
B.
John Simenon
John Simenon is the son and literary estate manager of Belgian novelist Georges Simenon, overseeing and promoting his father's works.
-
C.
Maxime Maufra
Maxime Maufra was a French landscape and marine painter associated with the Pont-Aven School and known for his post-Impressionist style and vivid use of color.
-
D.
Sébastien Japrisot
Sébastien Japrisot was a French novelist, screenwriter, and director known for his intricate crime and war stories, several of which were adapted into acclaimed films.
-
E.
Alban Préaubert
Alban Préaubert is a French former competitive figure skater known for his strong jumping ability and multiple top-ten finishes at European and World Championships.
- 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_69e0b4f675cc8190b4e745225b62eb66 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c45e51f08190ac1ff59280ad741b |
completed | April 21, 2026, 12:27 a.m. |
Created at: April 16, 2026, 12:44 p.m.