Triple
T18702187
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Erik Hilding Carlsson |
E457279
|
entity |
| Predicate | nickname |
P55
|
FINISHED |
| Object | Carlsson on the roof |
—
|
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: Carlsson on the roof | Statement: [Erik Hilding Carlsson, nickname, Carlsson on the roof]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Carlsson on the roof Context triple: [Erik Hilding Carlsson, nickname, Carlsson on the roof]
-
A.
Carlsson på taket
chosen
Carlsson på taket is a mischievous, self-confident man with a propeller on his back from Astrid Lindgren’s children’s books, known for living on a rooftop and causing humorous chaos.
-
B.
Carlsson
Carlsson is a surname of Scandinavian origin, commonly used in Sweden and other Nordic countries.
-
C.
Gothia Towers
Gothia Towers is a prominent hotel and conference complex in Gothenburg, Sweden, known for its three glass towers and central role in hosting major events and exhibitions.
-
D.
The Roof
"The Roof" is a song by Mariah Carey, known for its smooth R&B production and vivid storytelling about a romantic encounter.
-
E.
The Roof
The Roof is a film featuring British actor Arthur Margetson in a significant role.
- 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_69d8d392aad081909fe31aa03e6e97d1 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e56714d0588190ac050356bc2784fd |
completed | April 19, 2026, 11:36 p.m. |
Created at: April 10, 2026, 11:49 a.m.