Triple
T22008787
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kerli Kõiv |
E543519
|
entity |
| Predicate | hasCollaboratedWith |
P8554
|
FINISHED |
| Object | Tokio Hotel |
—
|
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: Tokio Hotel | Statement: [Kerli Kõiv, hasCollaboratedWith, Tokio Hotel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tokio Hotel Context triple: [Kerli Kõiv, hasCollaboratedWith, Tokio Hotel]
-
A.
Tokio Hotel
chosen
Tokio Hotel is a German pop-rock band that gained international fame in the mid-2000s with hits like "Monsoon" and a distinctive emo-inspired image.
-
B.
The Rasmus
The Rasmus is a Finnish rock band best known internationally for their 2003 hit single "In the Shadows."
-
C.
The Coronas
The Coronas are an Irish rock band known for their melodic, radio-friendly sound and success on the Irish music charts.
-
D.
The Cardigans
The Cardigans are a Swedish rock band best known internationally for their 1990s hits like "Lovefool," blending catchy pop melodies with alternative rock influences.
-
E.
Danjaq
Danjaq is the film production and rights-holding company best known for owning and controlling the James Bond movie franchise.
- 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_69e11e2db934819095556760c7d85e4d |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f127a2aebc8190951ee0bf9fd8e16d |
completed | April 28, 2026, 9:33 p.m. |
Created at: April 16, 2026, 8:21 p.m.