Triple
T7927025
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Heidi Klum |
E184090
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Tom Kaulitz
Tom Kaulitz is a German musician and guitarist best known as a member of the rock band Tokio Hotel.
|
E700288
|
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: Tom Kaulitz | Statement: [Heidi Klum, spouse, Tom Kaulitz]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tom Kaulitz Context triple: [Heidi Klum, spouse, Tom Kaulitz]
-
A.
John Kurzweg
John Kurzweg is an American record producer and musician best known for his work on successful rock and alternative albums in the late 1990s and early 2000s.
-
B.
Jonas Saur
Jonas Saur was an early 17th-century printer known for producing Johannes Kepler’s influential astronomical work, the Rudolphine Tables.
-
C.
Matthew Spitz
Matthew Spitz is known as one of the children of legendary American Olympic swimmer Mark Spitz.
-
D.
Erik von Detten
Erik von Detten is an American actor best known for his work in popular 1990s and 2000s films and television series, including notable voice roles in animated features.
-
E.
Christoph Probst
Christoph Probst was a German medical student and resistance fighter who was executed in 1943 for his involvement in the anti-Nazi White Rose movement.
- 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: Tom Kaulitz Triple: [Heidi Klum, spouse, Tom Kaulitz]
Generated description
Tom Kaulitz is a German musician and guitarist best known as a member of the rock band Tokio Hotel.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Tom Kaulitz Target entity description: Tom Kaulitz is a German musician and guitarist best known as a member of the rock band Tokio Hotel.
-
A.
John Kurzweg
John Kurzweg is an American record producer and musician best known for his work on successful rock and alternative albums in the late 1990s and early 2000s.
-
B.
Jonas Saur
Jonas Saur was an early 17th-century printer known for producing Johannes Kepler’s influential astronomical work, the Rudolphine Tables.
-
C.
Matthew Spitz
Matthew Spitz is known as one of the children of legendary American Olympic swimmer Mark Spitz.
-
D.
Erik von Detten
Erik von Detten is an American actor best known for his work in popular 1990s and 2000s films and television series, including notable voice roles in animated features.
-
E.
Christoph Probst
Christoph Probst was a German medical student and resistance fighter who was executed in 1943 for his involvement in the anti-Nazi White Rose movement.
- 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_69ca828fe7bc819090f52c88dcd72183 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb3aafdb5c8190b7f2ce5349305f78 |
completed | March 31, 2026, 3:08 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cb5bfd08e88190bc6b2d77a148ae57 |
completed | March 31, 2026, 5:30 a.m. |
| NEDg | Description generation | batch_69cb7633c5a0819089deb6e89d9acb8e |
completed | March 31, 2026, 7:22 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69cbb84dc86c8190893d67ce07c51aa0 |
completed | March 31, 2026, 12:04 p.m. |
Created at: March 30, 2026, 5:07 p.m.