Triple
T19790348
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Peter Maffay |
E475391
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Tanja Spengler
Tanja Spengler is known as the former wife of German rock musician Peter Maffay.
|
E1396313
|
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: Tanja Spengler | Statement: [Peter Maffay, spouse, Tanja Spengler]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tanja Spengler Context triple: [Peter Maffay, spouse, Tanja Spengler]
-
A.
Tanja Lange
Tanja Lange is a cryptographer known for her work on elliptic-curve cryptography and contributions to practical, high-security cryptographic software.
-
B.
Michaela Reichelt
Michaela Reichelt is a German local politician who serves as the mayor of the municipality of Inning am Ammersee in Bavaria.
-
C.
Verena Rehm
Verena Rehm is a German singer and songwriter best known as the female vocalist for the Eurodance project Groove Coverage.
-
D.
Heike Drechsler
Heike Drechsler is a German former track and field athlete best known as one of history’s greatest long jumpers, winning multiple Olympic and World Championship titles.
-
E.
Franziska Matzelsberger
Franziska Matzelsberger was the second wife of Alois Hitler and the stepmother of Adolf Hitler.
- 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: Tanja Spengler Triple: [Peter Maffay, spouse, Tanja Spengler]
Generated description
Tanja Spengler is known as the former wife of German rock musician Peter Maffay.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Tanja Spengler Target entity description: Tanja Spengler is known as the former wife of German rock musician Peter Maffay.
-
A.
Tanja Lange
Tanja Lange is a cryptographer known for her work on elliptic-curve cryptography and contributions to practical, high-security cryptographic software.
-
B.
Michaela Reichelt
Michaela Reichelt is a German local politician who serves as the mayor of the municipality of Inning am Ammersee in Bavaria.
-
C.
Verena Rehm
Verena Rehm is a German singer and songwriter best known as the female vocalist for the Eurodance project Groove Coverage.
-
D.
Heike Drechsler
Heike Drechsler is a German former track and field athlete best known as one of history’s greatest long jumpers, winning multiple Olympic and World Championship titles.
-
E.
Franziska Matzelsberger
Franziska Matzelsberger was the second wife of Alois Hitler and the stepmother of Adolf Hitler.
- 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_69d8e51b014081908b263e167370529a |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e653c217bc819092c517b27ca22087 |
completed | April 20, 2026, 4:26 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a07c4fdbf4c8190a9177e87b65fc965 |
completed | May 16, 2026, 1:14 a.m. |
| NEDg | Description generation | batch_6a07c90c07a48190b0f23597124b5017 |
completed | May 16, 2026, 1:31 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a07c97b33b481909e9b45b37cfe87b3 |
completed | May 16, 2026, 1:33 a.m. |
Created at: April 10, 2026, 1:49 p.m.