Triple
T17834474
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tegnergatan |
E445345
|
entity |
| Predicate | connectsWith |
P37
|
FINISHED |
| Object | Drottninggatan |
—
|
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: Drottninggatan | Statement: [Tegnergatan, connectsWith, Drottninggatan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Drottninggatan Context triple: [Tegnergatan, connectsWith, Drottninggatan]
-
A.
Drottninggatan
chosen
Drottninggatan is one of Stockholm’s main pedestrian shopping streets, known for its central location, stores, and restaurants.
-
B.
Kungsgatan
Kungsgatan is a major central street in Stockholm, Sweden, known for its early 20th-century architecture, bustling shops, and iconic twin towers.
-
C.
Regeringsgatan
Regeringsgatan is a major street in central Stockholm, Sweden, known for its shops, offices, and role as a key thoroughfare through the city center.
-
D.
Sveavägen
Sveavägen is a major thoroughfare in central Stockholm, Sweden, known for its commercial activity and historical significance.
-
E.
Kungsholmsgatan
Kungsholmsgatan is a street in central Stockholm, Sweden, located on the island of Kungsholmen.
- 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_69d8b9f1a6d881909f024bc603111cdb |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e48d271e4481909664897cb789fe4a |
completed | April 19, 2026, 8:07 a.m. |
Created at: April 10, 2026, 10:16 a.m.