Triple
T16303161
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mazda 787B |
E395839
|
entity |
| Predicate | driver |
P268
|
FINISHED |
| Object |
Volker Weidler
Volker Weidler is a former German racing driver best known for being part of the winning team at the 1991 24 Hours of Le Mans with Mazda.
|
E1559654
|
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: Volker Weidler | Statement: [Mazda 787B, driver, Volker Weidler]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Volker Weidler Context triple: [Mazda 787B, driver, Volker Weidler]
-
A.
Jürgen Büscher
Jürgen Büscher is a screenwriter best known for co-writing the 1993 German war film "Stalingrad."
-
B.
Jürgen Doering
Jürgen Doering is a costume designer known for his work on films such as "Personal Shopper."
-
C.
Ingo Rademacher
Ingo Rademacher is a German-Australian actor best known for his long-running role as Jasper "Jax" Jacks on the soap opera General Hospital.
-
D.
Eckhard Pfeiffer
Eckhard Pfeiffer is a German-American businessman best known for serving as CEO of Compaq Computer Corporation during its rapid expansion in the 1990s.
-
E.
Volker Jung
Volker Jung is a German Protestant theologian and church leader known for serving as president of the Protestant Church in Hesse and Nassau and for his engagement with contemporary social and ethical issues.
- 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: Volker Weidler Triple: [Mazda 787B, driver, Volker Weidler]
Generated description
Volker Weidler is a former German racing driver best known for being part of the winning team at the 1991 24 Hours of Le Mans with Mazda.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Volker Weidler Target entity description: Volker Weidler is a former German racing driver best known for being part of the winning team at the 1991 24 Hours of Le Mans with Mazda.
-
A.
Jürgen Büscher
Jürgen Büscher is a screenwriter best known for co-writing the 1993 German war film "Stalingrad."
-
B.
Jürgen Doering
Jürgen Doering is a costume designer known for his work on films such as "Personal Shopper."
-
C.
Ingo Rademacher
Ingo Rademacher is a German-Australian actor best known for his long-running role as Jasper "Jax" Jacks on the soap opera General Hospital.
-
D.
Eckhard Pfeiffer
Eckhard Pfeiffer is a German-American businessman best known for serving as CEO of Compaq Computer Corporation during its rapid expansion in the 1990s.
-
E.
Volker Jung
Volker Jung is a German Protestant theologian and church leader known for serving as president of the Protestant Church in Hesse and Nassau and for his engagement with contemporary social and ethical issues.
- 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_69d87f23bb088190a16fbb91a1957ea5 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e25e35157481909e5604b7dae7a2a2 |
completed | April 17, 2026, 4:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0bb9a3f4b081909478df83d6ff60c1 |
completed | May 19, 2026, 1:15 a.m. |
| NEDg | Description generation | batch_6a0bbb7ae63c8190b354049d60f310e5 |
completed | May 19, 2026, 1:23 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0bbbd421c48190a7202f2662b21011 |
completed | May 19, 2026, 1:24 a.m. |
Created at: April 10, 2026, 5:06 a.m.