Triple
T8603373
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Andreas Schelfhout |
E203733
|
entity |
| Predicate | student |
P7251
|
FINISHED |
| Object |
Charles Leickert
Charles Leickert was a 19th-century Dutch painter renowned for his atmospheric winter landscapes and cityscapes of the Netherlands.
|
E779996
|
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: Charles Leickert | Statement: [Andreas Schelfhout, student, Charles Leickert]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Charles Leickert Context triple: [Andreas Schelfhout, student, Charles Leickert]
-
A.
Charles Rettig
Charles Rettig is an American tax attorney who served as the Commissioner of the Internal Revenue Service (IRS) from 2018 to 2022.
-
B.
George Boemler
George Boemler was a film editor known for his work on classic Hollywood productions, including the musical comedy "High Society."
-
C.
Charles Deetz
Charles Deetz is a nervous, real-estate-obsessed father who moves his family into a haunted country house in the dark comedy film "Beetlejuice."
-
D.
J. C. Henneberger
J. C. Henneberger was an American publisher best known for creating and publishing the influential pulp horror and fantasy magazine Weird Tales.
-
E.
Arthur Hohl
Arthur Hohl was an American character actor known for his supporting roles in numerous Hollywood films during the 1930s and 1940s.
- 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: Charles Leickert Triple: [Andreas Schelfhout, student, Charles Leickert]
Generated description
Charles Leickert was a 19th-century Dutch painter renowned for his atmospheric winter landscapes and cityscapes of the Netherlands.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Charles Leickert Target entity description: Charles Leickert was a 19th-century Dutch painter renowned for his atmospheric winter landscapes and cityscapes of the Netherlands.
-
A.
Charles Rettig
Charles Rettig is an American tax attorney who served as the Commissioner of the Internal Revenue Service (IRS) from 2018 to 2022.
-
B.
George Boemler
George Boemler was a film editor known for his work on classic Hollywood productions, including the musical comedy "High Society."
-
C.
Charles Deetz
Charles Deetz is a nervous, real-estate-obsessed father who moves his family into a haunted country house in the dark comedy film "Beetlejuice."
-
D.
J. C. Henneberger
J. C. Henneberger was an American publisher best known for creating and publishing the influential pulp horror and fantasy magazine Weird Tales.
-
E.
Arthur Hohl
Arthur Hohl was an American character actor known for his supporting roles in numerous Hollywood films during the 1930s and 1940s.
- 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_69ca832b56948190ba751cec255308f1 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cc46dc23448190a5eb63455578427e |
completed | March 31, 2026, 10:12 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d0470dd24c8190851f71104c9fdf0f |
completed | April 3, 2026, 11:02 p.m. |
| NEDg | Description generation | batch_69d0489f19808190b793dac8c0f743bc |
completed | April 3, 2026, 11:09 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69d0496ccb908190b9ebe632df1447be |
completed | April 3, 2026, 11:12 p.m. |
Created at: March 30, 2026, 6:24 p.m.