Triple
T15073611
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gärdet |
E379941
|
entity |
| Predicate | hasLandmark |
P105
|
FINISHED |
| Object | Kaknästornet |
E1039076
|
NE FINISHED |
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: Kaknästornet | Statement: [Gärdet, hasLandmark, Kaknästornet]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kaknästornet Context triple: [Gärdet, hasLandmark, Kaknästornet]
-
A.
Kaknästornet
chosen
Kaknästornet is a prominent telecommunications and observation tower in Stockholm, Sweden, known for its modernist design and panoramic city views.
-
B.
Skarpnäck
Skarpnäck is a residential district in southern Stockholm, Sweden, known for its postwar housing areas and as the terminus of the green line on the Stockholm metro.
-
C.
Gustavsberg
Gustavsberg is a locality in Sweden best known for its historic porcelain factory and role as a suburban community in the Stockholm archipelago.
-
D.
Skarpäng
Skarpäng is a residential urban area within Täby Municipality in Stockholm County, Sweden.
-
E.
Klausberg
Klausberg is a mountain in the Italian Alps known for its scenic viewpoints, including the historic Belvedere on the Klausberg.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d85cd7683881908d405c1b5d7b4f7f |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69dff7fa0570819088a97b28173154cd |
completed | April 15, 2026, 8:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fea5cff69c8190b6252509c1aa7ebb |
completed | May 9, 2026, 3:11 a.m. |
Created at: April 10, 2026, 3:02 a.m.