Triple
T19991060
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hauser & Wirth |
E494064
|
entity |
| Predicate | foundedBy |
P104
|
FINISHED |
| Object |
Manuela Wirth
Manuela Wirth is a Swiss art dealer and co-founder of the influential international contemporary art gallery Hauser & Wirth.
|
E1407311
|
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: Manuela Wirth | Statement: [Hauser & Wirth, foundedBy, Manuela Wirth]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Manuela Wirth Context triple: [Hauser & Wirth, foundedBy, Manuela Wirth]
-
A.
Katrin Brenner
Katrin Brenner is a German local politician who serves as the mayor of the town of Sundern in North Rhine-Westphalia.
-
B.
Juliane Blasi
Juliane Blasi is an automotive designer best known for her work on BMW’s second-generation Z4 (E89) roadster.
-
C.
Franziska Matzelsberger
Franziska Matzelsberger was the second wife of Alois Hitler and the stepmother of Adolf Hitler.
-
D.
Juliane Lorenz
Juliane Lorenz is a German film editor best known for her long-standing collaboration with director Rainer Werner Fassbinder and for managing his film legacy.
-
E.
Michaela Dorfmeister
Michaela Dorfmeister is a retired Austrian alpine ski racer renowned for winning multiple World Cup titles and Olympic gold medals in the early 2000s.
- 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: Manuela Wirth Triple: [Hauser & Wirth, foundedBy, Manuela Wirth]
Generated description
Manuela Wirth is a Swiss art dealer and co-founder of the influential international contemporary art gallery Hauser & Wirth.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Manuela Wirth Target entity description: Manuela Wirth is a Swiss art dealer and co-founder of the influential international contemporary art gallery Hauser & Wirth.
-
A.
Katrin Brenner
Katrin Brenner is a German local politician who serves as the mayor of the town of Sundern in North Rhine-Westphalia.
-
B.
Juliane Blasi
Juliane Blasi is an automotive designer best known for her work on BMW’s second-generation Z4 (E89) roadster.
-
C.
Franziska Matzelsberger
Franziska Matzelsberger was the second wife of Alois Hitler and the stepmother of Adolf Hitler.
-
D.
Juliane Lorenz
Juliane Lorenz is a German film editor best known for her long-standing collaboration with director Rainer Werner Fassbinder and for managing his film legacy.
-
E.
Michaela Dorfmeister
Michaela Dorfmeister is a retired Austrian alpine ski racer renowned for winning multiple World Cup titles and Olympic gold medals in the early 2000s.
- 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_69da626a67648190af9653832a3aeced |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e65fe00b908190bda6b9a3a3281ec0 |
completed | April 20, 2026, 5:18 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a080e1c30c48190973e2735ecef8354 |
completed | May 16, 2026, 6:26 a.m. |
| NEDg | Description generation | batch_6a08100875fc8190a60561870c8b6e32 |
completed | May 16, 2026, 6:34 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a081080c9908190a6029049afe65004 |
completed | May 16, 2026, 6:36 a.m. |
Created at: April 11, 2026, 3:31 p.m.