Triple
T2593220
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Karolinska Institutet |
E58171
|
entity |
| Predicate | abbreviation |
P43
|
FINISHED |
| Object | KI |
E58171
|
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: KI | Statement: [Karolinska Institutet, abbreviation, KI]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: KI Context triple: [Karolinska Institutet, abbreviation, KI]
-
A.
KI
chosen
KI is the abbreviation for the Karolinska Institute, a renowned Swedish medical university known for its leading research and role in selecting Nobel laureates in Physiology or Medicine.
-
B.
Ki
Ki is the Sumerian earth goddess and primordial mother figure in Mesopotamian mythology, often paired with the sky god Anu in creation traditions.
-
C.
Kir
Kir is a classic French apéritif cocktail traditionally made by mixing dry white wine with crème de cassis (blackcurrant liqueur).
-
D.
KR
KR is the vehicle registration code used on license plates for the German city of Krefeld.
-
E.
KL
KL is the two-letter IATA airline code assigned to KLM Royal Dutch Airlines.
- 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_69ab4ac019c8819094add11c46706e32 |
completed | March 6, 2026, 9:44 p.m. |
| NER | Named-entity recognition | batch_69abd426e2d4819081a07920b4d2a1cc |
completed | March 7, 2026, 7:30 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69af83bee4908190b5e446ddbf4e8889 |
completed | March 10, 2026, 2:36 a.m. |
Created at: March 6, 2026, 9:49 p.m.