Triple
T19394966
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wien Hauptbahnhof |
E485162
|
entity |
| Predicate | architect |
P184
|
FINISHED |
| Object |
Theo Hotz
Theo Hotz was a prominent Swiss architect known for major transportation and infrastructure projects, including the design of Vienna’s main railway station.
|
E1373980
|
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: Theo Hotz | Statement: [Wien Hauptbahnhof, architect, Theo Hotz]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Theo Hotz Context triple: [Wien Hauptbahnhof, architect, Theo Hotz]
-
A.
William Schultz
William Schultz is a relatively common personal name shared by multiple individuals across various professions and public roles.
-
B.
John Eisendrath
John Eisendrath is a television writer and producer best known for his work on series such as "The Blacklist" and "Alias."
-
C.
Tenen Holtz
Tenen Holtz was a character actor known for his work in early American films and theater, often appearing in supporting roles during the 1920s and 1930s.
-
D.
Theo LeSieg
Theo LeSieg is a pen name used by beloved children's author Dr. Seuss for books he wrote but did not illustrate himself.
-
E.
Joe Zerhusen
Joe Zerhusen is an American sports broadcaster best known as a longtime radio voice associated with Cincinnati Reds baseball games.
- 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: Theo Hotz Triple: [Wien Hauptbahnhof, architect, Theo Hotz]
Generated description
Theo Hotz was a prominent Swiss architect known for major transportation and infrastructure projects, including the design of Vienna’s main railway station.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Theo Hotz Target entity description: Theo Hotz was a prominent Swiss architect known for major transportation and infrastructure projects, including the design of Vienna’s main railway station.
-
A.
William Schultz
William Schultz is a relatively common personal name shared by multiple individuals across various professions and public roles.
-
B.
John Eisendrath
John Eisendrath is a television writer and producer best known for his work on series such as "The Blacklist" and "Alias."
-
C.
Tenen Holtz
Tenen Holtz was a character actor known for his work in early American films and theater, often appearing in supporting roles during the 1920s and 1930s.
-
D.
Theo LeSieg
Theo LeSieg is a pen name used by beloved children's author Dr. Seuss for books he wrote but did not illustrate himself.
-
E.
Joe Zerhusen
Joe Zerhusen is an American sports broadcaster best known as a longtime radio voice associated with Cincinnati Reds baseball games.
- 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_69d8e8d5162481909db12435d9535c1a |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e61b47630881909ba390888b8779f6 |
completed | April 20, 2026, 12:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a072b8b87a881909b3651f98ab49cdb |
completed | May 15, 2026, 2:19 p.m. |
| NEDg | Description generation | batch_6a072eb2d5b08190a0cafb1427cfd16d |
completed | May 15, 2026, 2:33 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a072f6caef48190acb52960ebde9ace |
completed | May 15, 2026, 2:36 p.m. |
Created at: April 10, 2026, 1:36 p.m.