Triple
T4340849
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hötorgsskraporna |
E97574
|
entity |
| Predicate | hasBuilding |
P105
|
FINISHED |
| Object | Hötorgsskrapa 2 |
E97574
|
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: Hötorgsskrapa 2 | Statement: [Hötorgsskraporna, hasBuilding, Hötorgsskrapa 2]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hötorgsskrapa 2 Context triple: [Hötorgsskraporna, hasBuilding, Hötorgsskrapa 2]
-
A.
Hynnekleiv
Hynnekleiv is a small village in the municipality of Froland in Agder county, southern Norway.
-
B.
Hötorgsskraporna
chosen
Hötorgsskraporna are a group of five modernist high-rise office buildings in central Stockholm, notable for their uniform design and prominent place in the city’s skyline.
-
C.
Reykvíkingur
Reykvíkingur is the Icelandic term for a resident or native of Reykjavík, the capital city of Iceland.
-
D.
Lærdalsøyri
Lærdalsøyri is a historic village in western Norway known for its well-preserved wooden buildings and location at the inner end of the Sognefjord.
-
E.
Gleipnir
Gleipnir is the magically forged, deceptively thin binding in Norse mythology that successfully restrains the monstrous wolf Fenrir.
- 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_69b3454662a481908fbcd0bbfaa3a0a4 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b35170a6648190a15ffb21640ee478 |
completed | March 12, 2026, 11:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5db9fd4988190afa9e04b029cd573 |
completed | March 14, 2026, 10:05 p.m. |
Created at: March 12, 2026, 11:14 p.m.