Triple
T14179648
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Collège Royal de Rouen |
E351418
|
entity |
| Predicate | educated |
P5
|
FINISHED |
| Object |
Ernest Fauquet
Ernest Fauquet was a French scholar and educator associated with the Collège Royal de Rouen in the 19th century.
|
E1481593
|
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: Ernest Fauquet | Statement: [Collège Royal de Rouen, educated, Ernest Fauquet]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ernest Fauquet Context triple: [Collège Royal de Rouen, educated, Ernest Fauquet]
-
A.
Édouard Guillaud
Édouard Guillaud is a French Navy admiral who served as Chief of the Defence Staff of France in the early 2010s.
-
B.
Raymond Février
Raymond Février was a French architect best known for co-designing Madrid’s iconic Beaux-Arts style Edificio Metrópolis in the early 20th century.
-
C.
Pierre Authier
Pierre Authier is a French automotive designer best known for his work on contemporary Peugeot models, including the popular 208.
-
D.
Henri Villat
Henri Villat was a French mathematician known for his influential work in fluid mechanics and for holding a prominent chair at the Collège de France.
-
E.
Maurice Dorléac
Maurice Dorléac was a French actor and stage director best known as the father of actresses Catherine Deneuve and Françoise Dorléac.
- 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: Ernest Fauquet Triple: [Collège Royal de Rouen, educated, Ernest Fauquet]
Generated description
Ernest Fauquet was a French scholar and educator associated with the Collège Royal de Rouen in the 19th century.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Ernest Fauquet Target entity description: Ernest Fauquet was a French scholar and educator associated with the Collège Royal de Rouen in the 19th century.
-
A.
Édouard Guillaud
Édouard Guillaud is a French Navy admiral who served as Chief of the Defence Staff of France in the early 2010s.
-
B.
Raymond Février
Raymond Février was a French architect best known for co-designing Madrid’s iconic Beaux-Arts style Edificio Metrópolis in the early 20th century.
-
C.
Pierre Authier
Pierre Authier is a French automotive designer best known for his work on contemporary Peugeot models, including the popular 208.
-
D.
Henri Villat
Henri Villat was a French mathematician known for his influential work in fluid mechanics and for holding a prominent chair at the Collège de France.
-
E.
Maurice Dorléac
Maurice Dorléac was a French actor and stage director best known as the father of actresses Catherine Deneuve and Françoise Dorléac.
- 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_69d8278834a08190b0f1784e58d7b99c |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de61c90abc8190a9b9dc1f50db59fa |
completed | April 14, 2026, 3:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a09b40757c881908af169bb49628a28 |
completed | May 17, 2026, 12:26 p.m. |
| NEDg | Description generation | batch_6a09b77e73608190a21675b1bd7b8852 |
completed | May 17, 2026, 12:41 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a09b7e6888c8190ba9c22e38c47a773 |
completed | May 17, 2026, 12:43 p.m. |
Created at: April 10, 2026, 1:02 a.m.