Triple
T18760641
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Geldern |
E458759
|
entity |
| Predicate | hasMayor |
P185
|
FINISHED |
| Object |
Sven Kaiser
Sven Kaiser is a German local politician who serves as the mayor of the town of Geldern in North Rhine-Westphalia.
|
E1344910
|
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: Sven Kaiser | Statement: [Geldern, hasMayor, Sven Kaiser]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sven Kaiser Context triple: [Geldern, hasMayor, Sven Kaiser]
-
A.
Sven Wagner
Sven Wagner is a German local politician who serves as the mayor of the town of Aschersleben in Saxony-Anhalt.
-
B.
Andreas Senger
Andreas Senger is a person bearing the surname Senger, about whom no widely documented public information is available.
-
C.
Lars König
Lars König is a German local politician who serves as the mayor of the city of Witten in North Rhine-Westphalia.
-
D.
Carsten Dominik
Carsten Dominik is a software developer and astronomer best known as the original creator of Org-mode for Emacs.
-
E.
Ralf Kellermann
Ralf Kellermann is a German football manager best known for his successful tenure with VfL Wolfsburg’s women’s team, leading them to multiple domestic and European titles.
- 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: Sven Kaiser Triple: [Geldern, hasMayor, Sven Kaiser]
Generated description
Sven Kaiser is a German local politician who serves as the mayor of the town of Geldern in North Rhine-Westphalia.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Sven Kaiser Target entity description: Sven Kaiser is a German local politician who serves as the mayor of the town of Geldern in North Rhine-Westphalia.
-
A.
Sven Wagner
Sven Wagner is a German local politician who serves as the mayor of the town of Aschersleben in Saxony-Anhalt.
-
B.
Andreas Senger
Andreas Senger is a person bearing the surname Senger, about whom no widely documented public information is available.
-
C.
Lars König
Lars König is a German local politician who serves as the mayor of the city of Witten in North Rhine-Westphalia.
-
D.
Carsten Dominik
Carsten Dominik is a software developer and astronomer best known as the original creator of Org-mode for Emacs.
-
E.
Ralf Kellermann
Ralf Kellermann is a German football manager best known for his successful tenure with VfL Wolfsburg’s women’s team, leading them to multiple domestic and European titles.
- 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_69d8d395dba0819087568404508590cb |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e58d7ecca881909d6c262837b621b3 |
completed | April 20, 2026, 2:20 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a055bb46ef88190a5da0f3f7ebb3a38 |
completed | May 14, 2026, 5:20 a.m. |
| NEDg | Description generation | batch_6a055d8ac7cc81909fe88b26c568bbde |
completed | May 14, 2026, 5:28 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a055dbba9a481909a8c7c4c6bdab27f |
completed | May 14, 2026, 5:29 a.m. |
Created at: April 10, 2026, 11:52 a.m.