Triple
T974145
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Foxy Brown |
E21012
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object |
Marchand
Marchand is the surname of American rapper and actress Foxy Brown, whose full name is Inga DeCarlo Fung Marchand.
|
E115331
|
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: Marchand | Statement: [Foxy Brown, familyName, Marchand]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marchand Context triple: [Foxy Brown, familyName, Marchand]
-
A.
Jacques de Maleville
Jacques de Maleville was a French jurist and politician who played a key role as one of the principal drafters of France’s Civil Code under Napoleon.
-
B.
Bézu Fache
Bézu Fache is the stern and devout captain of the French Judicial Police who leads the investigation at the Louvre in Dan Brown’s novel *The Da Vinci Code*.
-
C.
Alphand
Alphand is a French surname most notably borne by Jean-Charles Adolphe Alphand, a 19th-century engineer known for designing many of Paris’s parks and boulevards.
-
D.
Stephen Sauvestre
Stephen Sauvestre was a French architect best known for designing the architectural embellishments and final aesthetic of the Eiffel Tower.
-
E.
Antoine
Antoine is the given name of Antoine de la Mothe Cadillac, the French explorer and founder of Detroit.
- 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: Marchand Triple: [Foxy Brown, familyName, Marchand]
Generated description
Marchand is the surname of American rapper and actress Foxy Brown, whose full name is Inga DeCarlo Fung Marchand.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Marchand Target entity description: Marchand is the surname of American rapper and actress Foxy Brown, whose full name is Inga DeCarlo Fung Marchand.
-
A.
Jacques de Maleville
Jacques de Maleville was a French jurist and politician who played a key role as one of the principal drafters of France’s Civil Code under Napoleon.
-
B.
Bézu Fache
Bézu Fache is the stern and devout captain of the French Judicial Police who leads the investigation at the Louvre in Dan Brown’s novel *The Da Vinci Code*.
-
C.
Alphand
Alphand is a French surname most notably borne by Jean-Charles Adolphe Alphand, a 19th-century engineer known for designing many of Paris’s parks and boulevards.
-
D.
Stephen Sauvestre
Stephen Sauvestre was a French architect best known for designing the architectural embellishments and final aesthetic of the Eiffel Tower.
-
E.
Antoine
Antoine is the given name of Antoine de la Mothe Cadillac, the French explorer and founder of Detroit.
- 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_69a493c2b62c8190b616351789ec47f8 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b460a5c0819087b03dfb8a3af2c2 |
completed | March 1, 2026, 9:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ac170a00f481909da0394531ac24fe |
completed | March 7, 2026, 12:16 p.m. |
| NEDg | Description generation | batch_69ac18e9be2081909770ab2ead56d0db |
completed | March 7, 2026, 12:24 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ac195b7cd08190b2c3f07d7ae849ed |
completed | March 7, 2026, 12:26 p.m. |
Created at: March 1, 2026, 7:40 p.m.