Triple
T21655633
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | University of Trier |
E534456
|
entity |
| Predicate | hasRector |
P325
|
FINISHED |
| Object |
Dorothee Heller
Dorothee Heller is a German academic who has served as rector (president) of the University of Trier.
|
E1496246
|
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: Dorothee Heller | Statement: [University of Trier, hasRector, Dorothee Heller]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dorothee Heller Context triple: [University of Trier, hasRector, Dorothee Heller]
-
A.
Gisela Hahn
Gisela Hahn is a German actress known for her roles in European genre films of the 1960s and 1970s.
-
B.
Gudrun Bichler
Gudrun Bichler is a fictional character from Elfriede Jelinek’s novel "Die Kinder der Toten," which explores themes of memory, trauma, and Austria’s Nazi past through experimental, ghostly narratives.
-
C.
Gisela Richter
Gisela Richter was a prominent German-born American classical archaeologist and art historian known for her influential work on Greek sculpture and vase painting.
-
D.
Hanni Ehlers
Hanni Ehlers is a German literary translator known for translating works of English-language authors into German.
-
E.
Carola Kurlbaum
Carola Kurlbaum was the wife of renowned architectural historian Nikolaus Pevsner and a significant personal influence and support throughout his career.
- 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: Dorothee Heller Triple: [University of Trier, hasRector, Dorothee Heller]
Generated description
Dorothee Heller is a German academic who has served as rector (president) of the University of Trier.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Dorothee Heller Target entity description: Dorothee Heller is a German academic who has served as rector (president) of the University of Trier.
-
A.
Gisela Hahn
Gisela Hahn is a German actress known for her roles in European genre films of the 1960s and 1970s.
-
B.
Gudrun Bichler
Gudrun Bichler is a fictional character from Elfriede Jelinek’s novel "Die Kinder der Toten," which explores themes of memory, trauma, and Austria’s Nazi past through experimental, ghostly narratives.
-
C.
Gisela Richter
Gisela Richter was a prominent German-born American classical archaeologist and art historian known for her influential work on Greek sculpture and vase painting.
-
D.
Hanni Ehlers
Hanni Ehlers is a German literary translator known for translating works of English-language authors into German.
-
E.
Carola Kurlbaum
Carola Kurlbaum was the wife of renowned architectural historian Nikolaus Pevsner and a significant personal influence and support throughout his career.
- 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_69e0c467e1f48190af2650b19175abc4 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef59185b208190a2cf4b8f54a2c231 |
completed | April 27, 2026, 12:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0a1e0fe61081908a1271ab0ae113c1 |
completed | May 17, 2026, 7:59 p.m. |
| NEDg | Description generation | batch_6a0a1ebd2bbc819083021cbc5873bfed |
completed | May 17, 2026, 8:02 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0a1fa12dbc8190a263b12f75ef073b |
completed | May 17, 2026, 8:05 p.m. |
Created at: April 16, 2026, 6:36 p.m.