Triple

T7651963
Position Surface form Disambiguated ID Type / Status
Subject Katarina Frostenson E173273 entity
Predicate notable work P4 FINISHED
Object Tankarna
Tankarna is a poetry collection by Swedish poet Katarina Frostenson, known for its dense, allusive language and exploration of memory, perception, and the limits of expression.
 E680329 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: Tankarna | Statement: [Katarina Frostenson, notable work, Tankarna]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Tankarna
Context triple: [Katarina Frostenson, notable work, Tankarna]
  • A. Tankavaara
    Tankavaara is a small village in Finnish Lapland known for its gold prospecting history and as a gateway to nearby wilderness areas.
  • B. Torvastad
    Torvastad is a coastal village in Karmøy municipality in Rogaland county, southwestern Norway.
  • C. Rycken
    Rycken is a Dutch-origin surname historically borne by families such as that of Abraham Rycken in the Low Countries and early colonial America.
  • D. Runhällen
    Runhällen is a small locality in central Sweden situated within Heby Municipality in Uppsala County.
  • E. Rombaken
    Rombaken is a fjord in northern Norway, known as an inner branch of the Ofotfjord near the town of Narvik.
  • 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: Tankarna
Triple: [Katarina Frostenson, notable work, Tankarna]
Generated description
Tankarna is a poetry collection by Swedish poet Katarina Frostenson, known for its dense, allusive language and exploration of memory, perception, and the limits of expression.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Tankarna
Target entity description: Tankarna is a poetry collection by Swedish poet Katarina Frostenson, known for its dense, allusive language and exploration of memory, perception, and the limits of expression.
  • A. Tankavaara
    Tankavaara is a small village in Finnish Lapland known for its gold prospecting history and as a gateway to nearby wilderness areas.
  • B. Torvastad
    Torvastad is a coastal village in Karmøy municipality in Rogaland county, southwestern Norway.
  • C. Rycken
    Rycken is a Dutch-origin surname historically borne by families such as that of Abraham Rycken in the Low Countries and early colonial America.
  • D. Runhällen
    Runhällen is a small locality in central Sweden situated within Heby Municipality in Uppsala County.
  • E. Rombaken
    Rombaken is a fjord in northern Norway, known as an inner branch of the Ofotfjord near the town of Narvik.
  • 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_69c6995473348190a4f41d110d619a18 completed March 27, 2026, 2:51 p.m.
NER Named-entity recognition batch_69c701770ac881909452348c9547ab47 completed March 27, 2026, 10:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69c89aeb66c081909f3a3d6385637c25 completed March 29, 2026, 3:22 a.m.
NEDg Description generation batch_69c89ed393648190a32cf9267968faf5 completed March 29, 2026, 3:38 a.m.
NED2 Entity disambiguation (via description) batch_69c89f35a7488190a6a9bc3d10bedd5a completed March 29, 2026, 3:40 a.m.
Created at: March 27, 2026, 3:58 p.m.