Triple
T13865242
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Francis, Duke of Beja |
E333304
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object |
Francis
Francis was a Portuguese infante of the House of Aviz who held the noble title of Duke of Beja in the 16th century.
|
E1066204
|
NE FINISHED |
How this triple was built (4 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: Francis | Statement: [Francis, Duke of Beja, givenName, Francis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Francis Context triple: [Francis, Duke of Beja, givenName, Francis]
-
A.
Francis
Francis is the given first name of Daley Thompson, the celebrated British decathlete and double Olympic gold medalist.
-
B.
Francis
Francis is the given first name of the American actor Frank Morgan, best known for his role as the Wizard in "The Wizard of Oz."
-
C.
Francis
Francis is the middle name of Samuel Francis Du Pont, a prominent 19th-century U.S. Navy admiral from the Du Pont family.
-
D.
Francis
Francis is the given first name of Scottish former professional footballer Frank McAvennie.
-
E.
Francis
Francis was the given name of Francis of Lorraine, a 16th-century French nobleman who became Duke of Lorraine and played a significant role in European dynastic politics.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Francis Triple: [Francis, Duke of Beja, givenName, Francis]
Generated description
Francis was a Portuguese infante of the House of Aviz who held the noble title of Duke of Beja in the 16th century.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Francis Target entity description: Francis was a Portuguese infante of the House of Aviz who held the noble title of Duke of Beja in the 16th century.
-
A.
Francis
Francis was a French prince of the House of Valois who held the title Duke of Anjou in the late 16th century.
-
B.
Francis
Francis, Duke of Guise, was a prominent 16th-century French nobleman and military leader known for his key role in the French Wars of Religion and his influence in the powerful House of Guise.
-
C.
Francis
Francis was the given name of Francis of Lorraine, a 16th-century French nobleman who became Duke of Lorraine and played a significant role in European dynastic politics.
-
D.
Francis
Francis was a German nobleman who served as Duke of Saxe-Coburg-Saalfeld in the late 18th and early 19th centuries.
-
E.
Francis
Francis, Duke of Longueville, was a French nobleman of the House of Orléans-Longueville who held significant territorial and political influence in early modern France.
- F. None of above. chosen
Provenance (5 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_69d81c5ced9c8190b0e9bcc6effe5959 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de05c30d9c81908217d41a3b4aaf85 |
completed | April 14, 2026, 9:15 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7c10113288190b799126d934df92a |
completed | May 3, 2026, 9:41 p.m. |
| NEDg | Description generation | batch_69f7c1e7efd88190ac07472647da69e7 |
completed | May 3, 2026, 9:45 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f7c3396f7c8190987079bf24ac8695 |
completed | May 3, 2026, 9:50 p.m. |
Created at: April 9, 2026, 10:14 p.m.