Triple
T13236286
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ice Station Zebra |
E315153
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object |
Alf Kjellin
Alf Kjellin was a Swedish actor and director known for his work in both European cinema and Hollywood films and television.
|
E1030002
|
NE FINISHED |
How this triple was built (4 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: Alf Kjellin | Statement: [Ice Station Zebra, castMember, Alf Kjellin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Alf Kjellin Context triple: [Ice Station Zebra, castMember, Alf Kjellin]
-
A.
Kjell Ödeen
Kjell Ödeen was a Swedish architect best known for designing major public buildings such as the Scandinavium arena in Gothenburg.
-
B.
Bengt Jansson
Bengt Jansson is a Swedish former speedway rider known for competing at international level during the 1960s and 1970s.
-
C.
Bertil Ohlsson
Bertil Ohlsson is a film producer best known for his work on the acclaimed drama "What's Eating Gilbert Grape."
-
D.
Kjell-Åke Andersson
Kjell-Åke Andersson is a Swedish football executive best known for his leadership role at the professional club Östersunds FK.
-
E.
Gunnar Wetterberg
Gunnar Wetterberg is a Swedish historian, author, and former diplomat known for his popular works on Nordic history and biographies of prominent Scandinavian figures.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Alf Kjellin Triple: [Ice Station Zebra, castMember, Alf Kjellin]
Generated description
Alf Kjellin was a Swedish actor and director known for his work in both European cinema and Hollywood films and television.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Alf Kjellin Target entity description: Alf Kjellin was a Swedish actor and director known for his work in both European cinema and Hollywood films and television.
-
A.
Kjell Ödeen
Kjell Ödeen was a Swedish architect best known for designing major public buildings such as the Scandinavium arena in Gothenburg.
-
B.
Bengt Jansson
Bengt Jansson is a Swedish former speedway rider known for competing at international level during the 1960s and 1970s.
-
C.
Bertil Ohlsson
Bertil Ohlsson is a film producer best known for his work on the acclaimed drama "What's Eating Gilbert Grape."
-
D.
Kjell-Åke Andersson
Kjell-Åke Andersson is a Swedish football executive best known for his leadership role at the professional club Östersunds FK.
-
E.
Gunnar Wetterberg
Gunnar Wetterberg is a Swedish historian, author, and former diplomat known for his popular works on Nordic history and biographies of prominent Scandinavian figures.
- F. None of above. chosen
Provenance (5 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_69d806b1072881909e46bd212259c5f0 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d98d56da008190af55da3a9e7ffd4d |
completed | April 10, 2026, 11:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f70a35ccc88190881a7066b7af8fea |
completed | May 3, 2026, 8:41 a.m. |
| NEDg | Description generation | batch_69f70c000da081909297f3d24666b6a5 |
completed | May 3, 2026, 8:49 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69f70ce60a7081908f9498fcfec98e90 |
completed | May 3, 2026, 8:52 a.m. |
Created at: April 9, 2026, 9:22 p.m.