Triple
T15992628
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tom Tykwer |
E387871
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Marie Steinmann
Marie Steinmann is a German film producer and philanthropist known for her work in cinema and her long-term partnership with director Tom Tykwer.
|
E1190453
|
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: Marie Steinmann | Statement: [Tom Tykwer, spouse, Marie Steinmann]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marie Steinmann Context triple: [Tom Tykwer, spouse, Marie Steinmann]
-
A.
Marie Ortmann
Marie Ortmann was the mother of aviation pioneer and Boeing Company founder William E. Boeing.
-
B.
Marie Thienemann
Marie Thienemann was the first wife of German dramatist and Nobel laureate Gerhart Hauptmann, known primarily through her association with his early life and career.
-
C.
Marie Meyer
Marie Meyer was the wife of the prominent German historian Eduard Meyer.
-
D.
Albertine Zehme
Albertine Zehme was a German actress and reciter best known for inspiring and performing the vocal role in Arnold Schoenberg’s groundbreaking melodrama "Pierrot Lunaire."
-
E.
Marie-Louise Vogt
Marie-Louise Vogt is known as the wife of British actor Richard Johnson.
- 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: Marie Steinmann Triple: [Tom Tykwer, spouse, Marie Steinmann]
Generated description
Marie Steinmann is a German film producer and philanthropist known for her work in cinema and her long-term partnership with director Tom Tykwer.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Marie Steinmann Target entity description: Marie Steinmann is a German film producer and philanthropist known for her work in cinema and her long-term partnership with director Tom Tykwer.
-
A.
Marie Ortmann
Marie Ortmann was the mother of aviation pioneer and Boeing Company founder William E. Boeing.
-
B.
Marie Thienemann
Marie Thienemann was the first wife of German dramatist and Nobel laureate Gerhart Hauptmann, known primarily through her association with his early life and career.
-
C.
Marie Meyer
Marie Meyer was the wife of the prominent German historian Eduard Meyer.
-
D.
Albertine Zehme
Albertine Zehme was a German actress and reciter best known for inspiring and performing the vocal role in Arnold Schoenberg’s groundbreaking melodrama "Pierrot Lunaire."
-
E.
Marie-Louise Vogt
Marie-Louise Vogt is known as the wife of British actor Richard Johnson.
- 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_69d86daa562c81908aacc179c0fe8fb5 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e157844ed881908b42bfc1bb740d4e |
completed | April 16, 2026, 9:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffcf1cb1388190b1ebccc6705e5974 |
completed | May 10, 2026, 12:19 a.m. |
| NEDg | Description generation | batch_69ffcf9d6c5c8190b10abdf70aed7ddf |
completed | May 10, 2026, 12:21 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ffd96de9288190ab1727e7864dcaa6 |
completed | May 10, 2026, 1:03 a.m. |
Created at: April 10, 2026, 4:54 a.m.