Triple
T16267021
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Claude d'Annebault |
E394901
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Claude d'Annebault |
E394901
|
NE FINISHED |
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: Claude d'Annebault | Statement: [Claude d'Annebault, name, Claude d'Annebault]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Claude d'Annebault Context triple: [Claude d'Annebault, name, Claude d'Annebault]
-
A.
Claude d'Annebault
chosen
Claude d'Annebault was a 16th-century French nobleman, admiral, and marshal who served as a leading military commander under King Francis I.
-
B.
Claude de Clermont
Claude de Clermont was a French noblewoman of the 16th century, best known as the mother of the Huguenot noble and jousting champion Gabriel de Montgomery.
-
C.
Antoine de Caux
Antoine de Caux was a military commander known for leading forces during the Siege of Acre.
-
D.
Jacques de Fariaux
Jacques de Fariaux was a 17th-century French military officer best known for commanding the defending forces during the 1673 siege of Maastricht in the Franco-Dutch War.
-
E.
Claude Dauphin
Claude Dauphin was a French actor known for his prolific film and stage career from the 1930s onward, often appearing in both French and international productions.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d87f221d8081909b0b2063e7528ba2 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e245c963ec8190b059fecac6248cd9 |
completed | April 17, 2026, 2:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a006798cf488190a68cf7e57902924e |
completed | May 10, 2026, 11:10 a.m. |
Created at: April 10, 2026, 5:05 a.m.