Triple
T36248998
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Free Hanseatic City of Bremen |
E891742
|
entity |
| Predicate | hasSecondCity |
P48850
|
FINISHED |
| Object | Bremerhaven |
—
|
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: Bremerhaven | Statement: [Free Hanseatic City of Bremen, hasSecondCity, Bremerhaven]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSecondCity Context triple: [Free Hanseatic City of Bremen, hasSecondCity, Bremerhaven]
-
A.
hasSecondaryCity
chosen
Indicates that an entity possesses or is associated with a secondary city in addition to its primary city.
-
B.
hasSecondaryAirport
Indicates that an entity is associated with an additional, typically smaller or alternative, airport beyond its primary one.
-
C.
isSecondLevelCityIn
Indicates that a city is classified as a second-level city within a specified administrative or territorial region.
-
D.
secondMetropolitan
Indicates that one entity is the second metropolitan (e.g., second-ranking or second-designated metropolitan authority or see) in relation to another entity.
-
E.
otherCity
Indicates that one city is different from and not the same as another city.
- F. None of above.
Provenance (3 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_69f76e4599108190811532e707d6bc2c |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a004a8892c08190bcacb952ad737716 |
completed | May 10, 2026, 9:06 a.m. |
| PD | Predicate disambiguation | batch_6a004a44b4948190be4b3dbfce8da020 |
completed | May 10, 2026, 9:05 a.m. |
Created at: May 3, 2026, 4:09 p.m.