Triple
T17834467
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tegnergatan |
E445345
|
entity |
| Predicate | connectsWith |
P37
|
FINISHED |
| Object | Vasagatan |
—
|
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: Vasagatan | Statement: [Tegnergatan, connectsWith, Vasagatan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Vasagatan Context triple: [Tegnergatan, connectsWith, Vasagatan]
-
A.
Vasagatan
chosen
Vasagatan is a major central street in Stockholm, Sweden, known for its busy traffic, shops, and proximity to Stockholm Central Station.
-
B.
Stora Värtan
Stora Värtan is a bay of the Baltic Sea in the Stockholm archipelago, known for its coastal residential areas, marinas, and recreational boating.
-
C.
Vesle
The Vesle is a river in northeastern France that flows through the Champagne region and was a significant geographic feature during World War I battles.
-
D.
Byälven
Byälven is a river in western Sweden that flows into Lake Vänern, contributing significantly to its water system.
-
E.
Dalälven
Dalälven is a major river in central Sweden known for its extensive watershed, hydroelectric power stations, and rich natural and recreational areas.
- 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.