Triple
T21533701
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paul Delaroche |
E531296
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object |
Delaroche
Delaroche is a French surname most notably associated with the 19th-century painter Paul Delaroche, known for his dramatic historical scenes.
|
E1489230
|
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: Delaroche | Statement: [Paul Delaroche, familyName, Delaroche]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Delaroche Context triple: [Paul Delaroche, familyName, Delaroche]
-
A.
de Guersaint
De Guersaint is a French surname historically associated with figures such as Marie de Guersaint.
-
B.
des Grassins
des Grassins is a French surname associated with the historical figure Guillaume des Grassins.
-
C.
Delacroix
Delacroix is a Brussels Metro station on line 2 located in the Anderlecht municipality of Brussels, Belgium.
-
D.
Ingres
Ingres is an early relational database management system that pioneered many concepts in modern database technology and influenced several later systems.
-
E.
Eduard "Del" Delacroix
Eduard "Del" Delacroix is a condemned Cajun inmate on death row in Stephen King’s "The Green Mile," known for his gentle bond with a trained mouse and his harrowingly botched execution.
- 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: Delaroche Triple: [Paul Delaroche, familyName, Delaroche]
Generated description
Delaroche is a French surname most notably associated with the 19th-century painter Paul Delaroche, known for his dramatic historical scenes.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Delaroche Target entity description: Delaroche is a French surname most notably associated with the 19th-century painter Paul Delaroche, known for his dramatic historical scenes.
-
A.
de Guersaint
De Guersaint is a French surname historically associated with figures such as Marie de Guersaint.
-
B.
des Grassins
des Grassins is a French surname associated with the historical figure Guillaume des Grassins.
-
C.
Delacroix
Delacroix is a Brussels Metro station on line 2 located in the Anderlecht municipality of Brussels, Belgium.
-
D.
Ingres
Ingres is an early relational database management system that pioneered many concepts in modern database technology and influenced several later systems.
-
E.
Eduard "Del" Delacroix
Eduard "Del" Delacroix is a condemned Cajun inmate on death row in Stephen King’s "The Green Mile," known for his gentle bond with a trained mouse and his harrowingly botched execution.
- 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_69e0c45e5b8881908ac18fc2f493b114 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ee9d0ae0e88190a6042effd93cd455 |
completed | April 26, 2026, 11:17 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a09e83156f48190aa472ffa77a4de57 |
completed | May 17, 2026, 4:09 p.m. |
| NEDg | Description generation | batch_6a09e8d6d1a88190b3f48111ed6a4043 |
completed | May 17, 2026, 4:12 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a09e94d6f2c819097df5c0a2b59e63a |
completed | May 17, 2026, 4:14 p.m. |
Created at: April 16, 2026, 6:27 p.m.