Triple
T21632875
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Novak |
E533877
|
entity |
| Predicate | hasNotableBearer |
P458
|
FINISHED |
| Object |
Jan Novak
Jan Novak is a common Czech personal name often used as a generic placeholder similar to "John Smith" in English.
|
E1494275
|
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: Jan Novak | Statement: [Novak, hasNotableBearer, Jan Novak]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jan Novak Context triple: [Novak, hasNotableBearer, Jan Novak]
-
A.
Richard Kovacevich
Richard Kovacevich is an American banker best known for serving as CEO and chairman of Wells Fargo.
-
B.
George Kralovansky
George Kralovansky is a television producer best known for his executive production work on the live law-enforcement reality series "Live PD."
-
C.
Martin Pasko
Martin Pasko was an American comic book and television writer best known for his work on DC Comics characters, particularly Superman and Batman, and for contributing to various animated series.
-
D.
John Novak
John Novak is the idealistic high-school English teacher protagonist of the 1960s American television drama series "Mr. Novak."
-
E.
John Sikela
John Sikela was a Golden Age comic book artist best known for his work on early Superman stories for DC Comics.
- 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: Jan Novak Triple: [Novak, hasNotableBearer, Jan Novak]
Generated description
Jan Novak is a common Czech personal name often used as a generic placeholder similar to "John Smith" in English.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Jan Novak Target entity description: Jan Novak is a common Czech personal name often used as a generic placeholder similar to "John Smith" in English.
-
A.
Richard Kovacevich
Richard Kovacevich is an American banker best known for serving as CEO and chairman of Wells Fargo.
-
B.
George Kralovansky
George Kralovansky is a television producer best known for his executive production work on the live law-enforcement reality series "Live PD."
-
C.
Martin Pasko
Martin Pasko was an American comic book and television writer best known for his work on DC Comics characters, particularly Superman and Batman, and for contributing to various animated series.
-
D.
John Novak
John Novak is the idealistic high-school English teacher protagonist of the 1960s American television drama series "Mr. Novak."
-
E.
John Sikela
John Sikela was a Golden Age comic book artist best known for his work on early Superman stories for DC Comics.
- 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_69e0c465ae7481908577b7209fdb2a77 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef52185dbc819096ad2fc5b7d953f8 |
completed | April 27, 2026, 12:10 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0a0f99a1b4819093788a4052d16b27 |
completed | May 17, 2026, 6:57 p.m. |
| NEDg | Description generation | batch_6a0a113126808190ba002d405cc9a3d6 |
completed | May 17, 2026, 7:04 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0a119cb17c8190a8732930b78b60cc |
completed | May 17, 2026, 7:06 p.m. |
Created at: April 16, 2026, 6:35 p.m.