Triple
T21891305
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Grand Bé |
E540553
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Petit Bé fort |
—
|
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: Petit Bé fort | Statement: [Grand Bé, near, Petit Bé fort]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Petit Bé fort Context triple: [Grand Bé, near, Petit Bé fort]
-
A.
Petit Bé fort
chosen
Petit Bé fort is a tidal island fortress off Saint-Malo, France, built in the late 17th century as part of the town’s coastal defenses.
-
B.
Petit Pic
Petit Pic is the lower of the two main summits of the Pic du Midi d’Ossau in the French Pyrenees, known for its rugged alpine climbing routes.
-
C.
Petitgout
Petitgout is a surname most notably associated with individuals such as former NFL offensive lineman Luke Petitgout.
-
D.
Bon-Bon
Bon-Bon is a common affectionate nickname, often used for people named Bonnie or for characters in popular media.
-
E.
Eclair Fifi
Eclair Fifi is a Scottish DJ, radio host, and visual artist known for her genre-spanning club sets and long-standing association with the LuckyMe collective.
- 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_69e0c47a95908190ae3e19b716accb3d |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f11fc3727c8190b4d5d5a44aa2e55e |
completed | April 28, 2026, 8:59 p.m. |
Created at: April 16, 2026, 7:06 p.m.