Triple
T19421650
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Robert de Craon |
E485869
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | de Craon |
—
|
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: de Craon | Statement: [Robert de Craon, familyName, de Craon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: de Craon Context triple: [Robert de Craon, familyName, de Craon]
-
A.
Craon
chosen
Craon is a small historic town in western France known for its château, horse-racing track, and rural charm within the Mayenne department.
-
B.
Eperlecques
Eperlecques is a commune in northern France best known for the nearby World War II V-2 rocket bunker known as the Blockhaus d'Éperlecques.
-
C.
La Guéroulde
La Guéroulde is a small commune in northern France, located in the Eure department of the Normandy region.
-
D.
Cap-d’Ail
Cap-d’Ail is a coastal resort town on the French Riviera, bordering Monaco and known for its scenic beaches and Belle Époque villas.
-
E.
Caulnes
Caulnes is a commune in the Côtes-d'Armor department in the Brittany region of northwestern France.
- 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_69d8e8d688f881909c85104a62e09d8a |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e63214d768819082129100d7116521 |
completed | April 20, 2026, 2:03 p.m. |
Created at: April 10, 2026, 1:37 p.m.