Triple
T21789012
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Corentin-Urbain Leissègues |
E537916
|
entity |
| Predicate | shipCommanded |
P884
|
FINISHED |
| Object | Impérial |
—
|
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: Impérial | Statement: [Corentin-Urbain Leissègues, shipCommanded, Impérial]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Impérial Context triple: [Corentin-Urbain Leissègues, shipCommanded, Impérial]
-
A.
Impérial
chosen
Impérial was a French 118-gun ship of the line that served as the flagship of the French fleet at the Battle of San Domingo during the Napoleonic Wars.
-
B.
Imperial
Imperial is the abbreviated name of Imperial Logistics, a major logistics and supply chain management company operating across multiple regions.
-
C.
Imperial
Imperial is a sprawling nonfiction work by William T. Vollmann that examines the history, politics, economy, and human cost of the U.S.–Mexico border region centered on California’s Imperial Valley.
-
D.
Imperial
Imperial is a coastal town in Peru’s Cañete Province known as a commercial and service hub for the surrounding agricultural region.
-
E.
Imperial
Imperial was Chrysler’s luxury automobile marque, created to compete with high-end brands like Cadillac and Lincoln in the American premium car market.
- 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_69e0c47198f881908cb0d237266c10e9 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f0621dfa3c8190921bfccbff7331f2 |
completed | April 28, 2026, 7:30 a.m. |
Created at: April 16, 2026, 6:52 p.m.