Triple
T18321963
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Georg Kolbe |
E438903
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Benjamine Kolbe
Benjamine Kolbe was the wife of renowned German sculptor Georg Kolbe and a member of his close artistic and personal circle.
|
E1318822
|
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: Benjamine Kolbe | Statement: [Georg Kolbe, spouse, Benjamine Kolbe]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Benjamine Kolbe Context triple: [Georg Kolbe, spouse, Benjamine Kolbe]
-
A.
Benjamin Kurtz
Benjamin Kurtz was a 19th-century Lutheran minister and educator best known for establishing Susquehanna University in Pennsylvania.
-
B.
Benjamin Kasulke
Benjamin Kasulke is an American cinematographer known for his work on independent films and collaborations with prominent indie directors.
-
C.
Kurt Huber
Kurt Huber was a German philosophy and psychology professor best known for his role as a member of the White Rose resistance group against the Nazi regime.
-
D.
Vít Korselt
Vít Korselt is a Czech diplomat who has served as the Czech Republic’s ambassador to the United States.
-
E.
Samuel Fischer
Samuel Fischer was a prominent German publisher best known for founding the influential S. Fischer Verlag, which played a key role in modern German literature.
- 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: Benjamine Kolbe Triple: [Georg Kolbe, spouse, Benjamine Kolbe]
Generated description
Benjamine Kolbe was the wife of renowned German sculptor Georg Kolbe and a member of his close artistic and personal circle.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Benjamine Kolbe Target entity description: Benjamine Kolbe was the wife of renowned German sculptor Georg Kolbe and a member of his close artistic and personal circle.
-
A.
Benjamin Kurtz
Benjamin Kurtz was a 19th-century Lutheran minister and educator best known for establishing Susquehanna University in Pennsylvania.
-
B.
Benjamin Kasulke
Benjamin Kasulke is an American cinematographer known for his work on independent films and collaborations with prominent indie directors.
-
C.
Kurt Huber
Kurt Huber was a German philosophy and psychology professor best known for his role as a member of the White Rose resistance group against the Nazi regime.
-
D.
Vít Korselt
Vít Korselt is a Czech diplomat who has served as the Czech Republic’s ambassador to the United States.
-
E.
Samuel Fischer
Samuel Fischer was a prominent German publisher best known for founding the influential S. Fischer Verlag, which played a key role in modern German literature.
- 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_69d8b916a2d081909e249e4902f6aad9 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e50aa7be288190983f13e9c7061b6d |
completed | April 19, 2026, 5:02 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a03c4c8224c819085369e23b7265dcb |
completed | May 13, 2026, 12:24 a.m. |
| NEDg | Description generation | batch_6a03c6397260819085b81b68cac69907 |
completed | May 13, 2026, 12:30 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a03c84f469c8190aef27154c17fd652 |
completed | May 13, 2026, 12:39 a.m. |
Created at: April 10, 2026, 10:36 a.m.