Triple
T19876844
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dubois |
E477660
|
entity |
| Predicate | hasNotableBearer |
P458
|
FINISHED |
| Object |
Pierre Dubois
Pierre Dubois is a French name shared by several notable figures, including politicians, scholars, and artists.
|
E1456131
|
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: Pierre Dubois | Statement: [Dubois, hasNotableBearer, Pierre Dubois]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pierre Dubois Context triple: [Dubois, hasNotableBearer, Pierre Dubois]
-
A.
Pierre Juneau
Pierre Juneau was a Canadian broadcasting executive and cultural policymaker who played a key role in promoting Canadian content and shaping the country’s media landscape.
-
B.
Pierre Lafue
Pierre Lafue was a French writer and intellectual whose legacy is honored by a literary foundation prize bearing his name.
-
C.
Edmond Beloin
Edmond Beloin was an American screenwriter and radio writer known for his work on Hollywood films and popular radio comedies in the mid-20th century.
-
D.
Pierre LeBrun
Pierre LeBrun was an American architect of the early 20th century known for designing prominent skyscrapers and commercial buildings, particularly in New York City.
-
E.
Ambroise Dupont
Ambroise Dupont was a 19th-century French publisher known for issuing works such as Émile Zola’s novel "Thérèse Raquin."
- 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: Pierre Dubois Triple: [Dubois, hasNotableBearer, Pierre Dubois]
Generated description
Pierre Dubois is a French name shared by several notable figures, including politicians, scholars, and artists.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Pierre Dubois Target entity description: Pierre Dubois is a French name shared by several notable figures, including politicians, scholars, and artists.
-
A.
Pierre Juneau
Pierre Juneau was a Canadian broadcasting executive and cultural policymaker who played a key role in promoting Canadian content and shaping the country’s media landscape.
-
B.
Pierre Lafue
Pierre Lafue was a French writer and intellectual whose legacy is honored by a literary foundation prize bearing his name.
-
C.
Edmond Beloin
Edmond Beloin was an American screenwriter and radio writer known for his work on Hollywood films and popular radio comedies in the mid-20th century.
-
D.
Pierre LeBrun
Pierre LeBrun was an American architect of the early 20th century known for designing prominent skyscrapers and commercial buildings, particularly in New York City.
-
E.
Ambroise Dupont
Ambroise Dupont was a 19th-century French publisher known for issuing works such as Émile Zola’s novel "Thérèse Raquin."
- 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_69d8e51f32b08190b3687f4f60353250 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e658dbdb648190b423865e7994a8fe |
completed | April 20, 2026, 4:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0918b234588190ac3b70bf4a3220e6 |
completed | May 17, 2026, 1:24 a.m. |
| NEDg | Description generation | batch_6a091971e5308190acdf4a65b1e67118 |
completed | May 17, 2026, 1:27 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0919f58008819097e05a187ed4b3de |
completed | May 17, 2026, 1:29 a.m. |
Created at: April 10, 2026, 1:52 p.m.