Triple
T12966704
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Żagań Piasts |
E321279
|
entity |
| Predicate | usedTitle |
P3254
|
FINISHED |
| Object |
dux Sagan
dux Sagan was a medieval ducal title associated with the Piast rulers of the Silesian town and region of Żagań.
|
E1013187
|
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: dux Sagan | Statement: [Żagań Piasts, usedTitle, dux Sagan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: dux Sagan Context triple: [Żagań Piasts, usedTitle, dux Sagan]
-
A.
Schwartzman
Schwartzman is a surname most notably associated with several American film industry figures, including cinematographer John Schwartzman and members of the Coppola family.
-
B.
Christian König
Christian König is a German politician and member of the Christian Democratic Union (CDU) known for his work in regional and national politics.
-
C.
Nico van der Lely
Nico van der Lely is a Dutch pediatrician known for his work on alcohol prevention and treatment among young people in the Netherlands.
-
D.
Timo Sauter
Timo Sauter is an individual notable enough to be recognized as a bearer of the surname Sauter, though specific widely known public information about him is limited.
-
E.
Sven Marnach
Sven Marnach is a software developer and Python contributor known for co-authoring PEP 636, which explains the language’s structural pattern matching feature.
- 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: dux Sagan Triple: [Żagań Piasts, usedTitle, dux Sagan]
Generated description
dux Sagan was a medieval ducal title associated with the Piast rulers of the Silesian town and region of Żagań.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: dux Sagan Target entity description: dux Sagan was a medieval ducal title associated with the Piast rulers of the Silesian town and region of Żagań.
-
A.
Schwartzman
Schwartzman is a surname most notably associated with several American film industry figures, including cinematographer John Schwartzman and members of the Coppola family.
-
B.
Christian König
Christian König is a German politician and member of the Christian Democratic Union (CDU) known for his work in regional and national politics.
-
C.
Nico van der Lely
Nico van der Lely is a Dutch pediatrician known for his work on alcohol prevention and treatment among young people in the Netherlands.
-
D.
Timo Sauter
Timo Sauter is an individual notable enough to be recognized as a bearer of the surname Sauter, though specific widely known public information about him is limited.
-
E.
Sven Marnach
Sven Marnach is a software developer and Python contributor known for co-authoring PEP 636, which explains the language’s structural pattern matching feature.
- 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_69d80763bd6c819094437da5b20b01d2 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69d97e3f702481908f0f90f4f12d3f4d |
completed | April 10, 2026, 10:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6b8e4e1a48190b8f7253717746295 |
completed | May 3, 2026, 2:54 a.m. |
| NEDg | Description generation | batch_69f6b9db8164819086a3a27692d681d5 |
completed | May 3, 2026, 2:58 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69f6bb337b708190a874cec01d588236 |
completed | May 3, 2026, 3:04 a.m. |
Created at: April 9, 2026, 8:30 p.m.