Triple
T8937967
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Berlin-Lichtenberg |
E212823
|
entity |
| Predicate | hasBoroughMayor |
P185
|
FINISHED |
| Object |
Michael Grunst
Michael Grunst is a German local politician who serves as the borough mayor of Berlin’s Lichtenberg district.
|
E786700
|
NE FINISHED |
How this triple was built (5 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: Michael Grunst | Statement: [Berlin-Lichtenberg, hasBoroughMayor, Michael Grunst]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michael Grunst Context triple: [Berlin-Lichtenberg, hasBoroughMayor, Michael Grunst]
-
A.
Michael Engelhart
Michael Engelhart was an architect known for his role in the post-war reconstruction of Vienna’s historic Burgtheater.
-
B.
Christopher Lennertz
Christopher Lennertz is an American composer best known for his film, television, and video game scores, including work on major comedies, action films, and popular series like Supernatural.
-
C.
Michael Ohoven
Michael Ohoven is a German film producer and founder of Infinity Media, known for producing acclaimed independent films such as "Capote."
-
D.
Matt Kaufmann
Matt Kaufmann is a computer scientist best known for his work on automated theorem proving and the ACL2 theorem prover, often in collaboration with J Strother Moore.
-
E.
Daniel Roher
Daniel Roher is a Canadian documentary filmmaker best known for directing the Oscar-winning political documentary "Navalny."
- 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: Michael Grunst Triple: [Berlin-Lichtenberg, hasBoroughMayor, Michael Grunst]
Generated description
Michael Grunst is a German local politician who serves as the borough mayor of Berlin’s Lichtenberg district.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Michael Grunst Target entity description: Michael Grunst is a German local politician who serves as the borough mayor of Berlin’s Lichtenberg district.
-
A.
Michael Engelhart
Michael Engelhart was an architect known for his role in the post-war reconstruction of Vienna’s historic Burgtheater.
-
B.
Christopher Lennertz
Christopher Lennertz is an American composer best known for his film, television, and video game scores, including work on major comedies, action films, and popular series like Supernatural.
-
C.
Michael Ohoven
Michael Ohoven is a German film producer and founder of Infinity Media, known for producing acclaimed independent films such as "Capote."
-
D.
Matt Kaufmann
Matt Kaufmann is a computer scientist best known for his work on automated theorem proving and the ACL2 theorem prover, often in collaboration with J Strother Moore.
-
E.
Daniel Roher
Daniel Roher is a Canadian documentary filmmaker best known for directing the Oscar-winning political documentary "Navalny."
- F. None of above. chosen
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasBoroughMayor Context triple: [Berlin-Lichtenberg, hasBoroughMayor, Michael Grunst]
-
A.
hasBoroughPresident
Indicates that a borough is associated with a specific individual who serves as its president or chief elected official.
-
B.
hasMayor
chosen
Indicates that one entity serves as the mayor of another entity, typically a city, town, or municipality.
-
C.
isBoroughSeatOf
Indicates that a place serves as the administrative center or seat of government for a specific borough.
-
D.
hasBoroughPresidentJurisdiction
Indicates that a borough president has official authority or administrative jurisdiction over a specified geographic or political area.
-
E.
hasBoroughCouncil
Indicates that an administrative area is governed or overseen by a specific borough council.
- F. None of above.
Provenance (6 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_69ca839694c88190b324ffeb43d23b08 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc66b57a348190979effe4f9998eb7 |
completed | April 1, 2026, 12:28 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d0773aee148190ad4da1b91271e48c |
completed | April 4, 2026, 2:28 a.m. |
| NEDg | Description generation | batch_69d07c2dffd0819096e3614d68ecdcc2 |
completed | April 4, 2026, 2:49 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69d07c8549688190a125ef09720c933b |
completed | April 4, 2026, 2:50 a.m. |
| PD | Predicate disambiguation | batch_69cc5ed5267c8190a43feb2a2f3df1ec |
completed | March 31, 2026, 11:55 p.m. |
Created at: March 30, 2026, 6:58 p.m.