Triple
T26981445
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Klanger och spår |
E679609
|
entity |
| Predicate | isWorkByNobelLaureate |
P131058
|
FINISHED |
| Object | Tomas Tranströmer |
—
|
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: Tomas Tranströmer | Statement: [Klanger och spår, isWorkByNobelLaureate, Tomas Tranströmer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isWorkByNobelLaureate Context triple: [Klanger och spår, isWorkByNobelLaureate, Tomas Tranströmer]
-
A.
appearsInWorkByNobelLaureate
chosen
Indicates that an entity appears in a work created by an individual who has received a Nobel Prize.
-
B.
hasAuthorNobelEquivalent
Indicates that the author of the work has received an award considered equivalent in prestige or recognition to a Nobel Prize in their field.
-
C.
roleInNobelPrize
Indicates the specific capacity or function an entity had in relation to a particular Nobel Prize (e.g., laureate, nominee, organization, or associated role).
-
D.
NobelPrizeCoLaureate
Indicates that two or more individuals share the same Nobel Prize as co-recipients for a particular award and year.
-
E.
hasLaureate
Indicates that an entity (such as an award or prize) has a specific person or group as its laureate or recipient.
- F. None of above.
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_69eeeb507a7081909d516e1fa08b7d29 |
completed | April 27, 2026, 4:51 a.m. |
| NER | Named-entity recognition | batch_69f621571b788190969da6a082eb93f6 |
completed | May 2, 2026, 4:07 p.m. |
| PD | Predicate disambiguation | batch_69f611af72ac819094598dd2530d7411 |
completed | May 2, 2026, 3:01 p.m. |
Created at: April 27, 2026, 6:46 a.m.