Triple
T20156444
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kastellholmen |
E491580
|
entity |
| Predicate | hasLandmark |
P105
|
FINISHED |
| Object | Kastellet |
—
|
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: Kastellet | Statement: [Kastellholmen, hasLandmark, Kastellet]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kastellet Context triple: [Kastellholmen, hasLandmark, Kastellet]
-
A.
Kastel
Kastel is a district of Mainz in Germany, historically part of the Rhine river region and known as the birthplace of brewing magnate Adolphus Busch.
-
B.
Kastellet fortress
chosen
Kastellet fortress is a well-preserved 17th-century star-shaped military fortification in Copenhagen, Denmark, now serving as a historic site and public park.
-
C.
Castelo
Castelo is one of Lisbon’s oldest hilltop neighborhoods, known for its medieval streets, historic castle, and panoramic views over the city and the Tagus River.
-
D.
Aros Castle
Aros Castle is a ruined medieval stronghold on the Isle of Mull in Scotland, historically associated with the powerful Clan Maclean.
-
E.
Dünamünde Fortress
Dünamünde Fortress was a former military stronghold near Riga that later served as a state prison, notably used to confine Russian regent Anna Leopoldovna.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69da6265f8f0819080b29c752a574088 |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e667e0a0488190a25d92aaf300be4a |
completed | April 20, 2026, 5:52 p.m. |
Created at: April 11, 2026, 11:34 p.m.