Triple
T20421156
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Oberhauser |
E500852
|
entity |
| Predicate | hasNotableBearer |
P458
|
FINISHED |
| Object |
Andrea Oberhauser
Andrea Oberhauser is an individual notable enough to be recognized as a prominent bearer of the surname Oberhauser.
|
E1429124
|
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: Andrea Oberhauser | Statement: [Oberhauser, hasNotableBearer, Andrea Oberhauser]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Andrea Oberhauser Context triple: [Oberhauser, hasNotableBearer, Andrea Oberhauser]
-
A.
Andrea Renner
Andrea Renner is a notable individual who shares the Renner surname, recognized enough to be specifically cited as a bearer of the name.
-
B.
Nicole Kruspe
Nicole Kruspe is a linguist known for her extensive research and documentation of Aslian languages spoken by indigenous communities in the Malay Peninsula.
-
C.
Andrea Richter
Andrea Richter is a television producer best known for creating the reality competition series "Ink Master."
-
D.
Andrea Sawatzki
Andrea Sawatzki is a German actress and author best known for her roles in film and television, including the long-running crime series "Tatort."
-
E.
Andrea Berndt
Andrea Berndt is known as the wife of American screenwriter and producer William Broyles Jr.
- 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: Andrea Oberhauser Triple: [Oberhauser, hasNotableBearer, Andrea Oberhauser]
Generated description
Andrea Oberhauser is an individual notable enough to be recognized as a prominent bearer of the surname Oberhauser.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Andrea Oberhauser Target entity description: Andrea Oberhauser is an individual notable enough to be recognized as a prominent bearer of the surname Oberhauser.
-
A.
Andrea Renner
Andrea Renner is a notable individual who shares the Renner surname, recognized enough to be specifically cited as a bearer of the name.
-
B.
Nicole Kruspe
Nicole Kruspe is a linguist known for her extensive research and documentation of Aslian languages spoken by indigenous communities in the Malay Peninsula.
-
C.
Andrea Richter
Andrea Richter is a television producer best known for creating the reality competition series "Ink Master."
-
D.
Andrea Sawatzki
Andrea Sawatzki is a German actress and author best known for her roles in film and television, including the long-running crime series "Tatort."
-
E.
Andrea Berndt
Andrea Berndt is known as the wife of American screenwriter and producer William Broyles Jr.
- 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_69e0b4aa68fc8190b1a14c55575ef04a |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e67ba479008190bf6d31ee79f3a401 |
completed | April 20, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a087b2c59a481908de9ca46fe4e8a9c |
completed | May 16, 2026, 2:11 p.m. |
| NEDg | Description generation | batch_6a088017be588190ab94b8180e44ebf4 |
completed | May 16, 2026, 2:32 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0880c45e1081908f439ade0c31a47e |
completed | May 16, 2026, 2:35 p.m. |
Created at: April 16, 2026, 11:30 a.m.