Triple
T22100274
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kings of the Road |
E546149
|
entity |
| Predicate | soundDesignBy |
P32563
|
FINISHED |
| Object |
Martin Müller
Martin Müller is a sound designer known for his work on the acclaimed German road movie "Kings of the Road" directed by Wim Wenders.
|
E1518713
|
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: Martin Müller | Statement: [Kings of the Road, soundDesignBy, Martin Müller]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Martin Müller Context triple: [Kings of the Road, soundDesignBy, Martin Müller]
-
A.
Marx Müller
Marx Müller was a historical builder and craftsman known for his role in constructing the Hofkirche in Innsbruck, Austria.
-
B.
Karsten Mußler
Karsten Mußler is a German local politician who serves as the mayor of the town of Kuppenheim in Baden-Württemberg.
-
C.
Dirk Weissenborn
Dirk Weissenborn is a computer vision and machine learning researcher known for co-introducing the Vision Transformer (ViT) architecture.
-
D.
Matthias Müller
Matthias Müller is a German local politician who serves as the mayor of the town of Herten.
-
E.
Christian Müller
Christian Müller was an 18th-century German-Dutch organ builder renowned for constructing some of the most celebrated baroque pipe organs in the Netherlands.
- 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: Martin Müller Triple: [Kings of the Road, soundDesignBy, Martin Müller]
Generated description
Martin Müller is a sound designer known for his work on the acclaimed German road movie "Kings of the Road" directed by Wim Wenders.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Martin Müller Target entity description: Martin Müller is a sound designer known for his work on the acclaimed German road movie "Kings of the Road" directed by Wim Wenders.
-
A.
Marx Müller
Marx Müller was a historical builder and craftsman known for his role in constructing the Hofkirche in Innsbruck, Austria.
-
B.
Karsten Mußler
Karsten Mußler is a German local politician who serves as the mayor of the town of Kuppenheim in Baden-Württemberg.
-
C.
Dirk Weissenborn
Dirk Weissenborn is a computer vision and machine learning researcher known for co-introducing the Vision Transformer (ViT) architecture.
-
D.
Matthias Müller
Matthias Müller is a German local politician who serves as the mayor of the town of Herten.
-
E.
Christian Müller
Christian Müller was an 18th-century German-Dutch organ builder renowned for constructing some of the most celebrated baroque pipe organs in the Netherlands.
- 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_69e11e378dc08190896d6a51597afd5a |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f1291440048190992c48893ced0b34 |
completed | April 28, 2026, 9:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0a87a38d2481909392e12f56d6d713 |
completed | May 18, 2026, 3:29 a.m. |
| NEDg | Description generation | batch_6a0a8a49535881908538d03581de240b |
completed | May 18, 2026, 3:40 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0a8ad24bcc81908fc15fd05295334b |
completed | May 18, 2026, 3:43 a.m. |
Created at: April 16, 2026, 8:30 p.m.