Triple
T28143737
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Berlin Senate for Culture |
E714418
|
entity |
| Predicate | hasCapitalCityAsJurisdiction |
P188878
|
FINISHED |
| Object | Berlin |
—
|
NE NERFINISHED |
How this triple was built (2 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: Berlin | Statement: [Berlin Senate for Culture, hasCapitalCityAsJurisdiction, Berlin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCapitalCityAsJurisdiction Context triple: [Berlin Senate for Culture, hasCapitalCityAsJurisdiction, Berlin]
-
A.
hasCapitalCityWithin
Indicates that a specified capital city is geographically located within the boundaries of a given region or country.
-
B.
hasCapitalCityOfContainingUnit
Indicates that a capital city belongs to and is located within a particular larger administrative or territorial unit.
-
C.
hasCapitalDistrictStatus
Indicates that an administrative region holds the official status of being a capital district within a country or larger jurisdiction.
-
D.
hasCapitalAdministered
Indicates that a specified capital city is responsible for administering or governing a particular territory or political entity.
-
E.
hasSovereignStateCapital
Indicates that a sovereign state has a specific city or location serving as its official capital.
- F. None of above. chosen
Provenance (4 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_69efd6b033208190bf74f80a147e2092 |
completed | April 27, 2026, 9:35 p.m. |
| NER | Named-entity recognition | batch_69fbaf18085481908c774e8f8bbb9a41 |
completed | May 6, 2026, 9:14 p.m. |
| PD | Predicate disambiguation | batch_69fbadf1e6008190a71bbd196ba06844 |
completed | May 6, 2026, 9:09 p.m. |
| PDg | Predicate description generation | batch_69fbaebbb7f88190b4edfd9b83550aad |
completed | May 6, 2026, 9:12 p.m. |
Created at: April 27, 2026, 9:55 p.m.