Triple
T22233366
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marais Viljoen |
E549524
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Marais |
—
|
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: Marais | Statement: [Marais Viljoen, givenName, Marais]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marais Context triple: [Marais Viljoen, givenName, Marais]
-
A.
Marais
chosen
Marais is a French-origin surname common in South Africa and other Francophone-influenced regions, borne by various notable figures in fields such as science, literature, and the arts.
-
B.
Marais
Marais is a historic district in central Paris known for its preserved medieval streets, elegant hôtels particuliers, vibrant Jewish and LGBTQ+ communities, and numerous museums and boutiques.
-
C.
L’Ecrin
L’Ecrin is the fine-dining gastronomic restaurant located within the luxury Hôtel de Crillon in Paris.
-
D.
L'Étang-la-Ville
L'Étang-la-Ville is a small, affluent suburban commune in the Yvelines department of north-central France, known for its wooded surroundings and residential character west of Paris.
-
E.
La Pallice
La Pallice is the deep-water commercial port district of La Rochelle on France’s Atlantic coast, known for its industrial docks and maritime facilities.
- 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_69e11e4102b881909cf47d3768e25c19 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f12bf4e0348190b755a9ac0bc96cdd |
completed | April 28, 2026, 9:51 p.m. |
Created at: April 16, 2026, 8:38 p.m.