Triple
T17715673
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cuvier Grover |
E442191
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Cuvier |
—
|
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: Cuvier | Statement: [Cuvier Grover, givenName, Cuvier]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cuvier Context triple: [Cuvier Grover, givenName, Cuvier]
-
A.
Cuvier
Cuvier is the surname of Georges Cuvier, a pioneering French naturalist and zoologist regarded as the founder of comparative anatomy and paleontology.
-
B.
Cuvier Grover
chosen
Cuvier Grover was a Union Army general during the American Civil War, noted for his leadership in several major campaigns and battles.
-
C.
Gressier
Gressier is a coastal commune in western Haiti known for its proximity to Port-au-Prince and its vulnerability to earthquakes and hurricanes.
-
D.
Everardus
Everardus is a Latinized given name historically used in medieval and early modern Europe, derived from the Germanic name Everard.
-
E.
Janenschia
Janenschia is a genus of large sauropod dinosaur from the Late Jurassic of what is now Tanzania, known for its long neck and massive body.
- 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_69d8b9ec79688190b86bdcef85a7b3aa |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e47480955481908fa0d3d34aaedd48 |
completed | April 19, 2026, 6:21 a.m. |
Created at: April 10, 2026, 10:06 a.m.