Triple

T16037621
Position Surface form Disambiguated ID Type / Status
Subject Astrid Lindgren E389008 entity
Predicate employer P7 FINISHED
Object Rabén & Sjögren
Rabén & Sjögren is a Swedish publishing house best known for its influential children's and young adult literature, including works by Astrid Lindgren.
 E1190947 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: Rabén & Sjögren | Statement: [Astrid Lindgren, employer, Rabén & Sjögren]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Rabén & Sjögren
Context triple: [Astrid Lindgren, employer, Rabén & Sjögren]
  • A. Löfgren
    Löfgren is a Swedish surname associated with several notable individuals in fields such as music, science, and politics.
  • B. Gotaas-Larsen
    Gotaas-Larsen was a Norwegian shipping company and maritime enterprise that played a key role in the early development of modern cruise operations.
  • C. Krabbé
    Krabbé is a Dutch surname most notably associated with actor and director Jeroen Krabbé.
  • D. Fischmann
    Fischmann is a surname variant of Fishman, typically of Ashkenazi Jewish origin.
  • E. Vogt-Roberts
    Vogt-Roberts is the hyphenated surname of American film director Jordan Vogt-Roberts, known for works like "Kong: Skull Island."
  • 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: Rabén & Sjögren
Triple: [Astrid Lindgren, employer, Rabén & Sjögren]
Generated description
Rabén & Sjögren is a Swedish publishing house best known for its influential children's and young adult literature, including works by Astrid Lindgren.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Rabén & Sjögren
Target entity description: Rabén & Sjögren is a Swedish publishing house best known for its influential children's and young adult literature, including works by Astrid Lindgren.
  • A. Löfgren
    Löfgren is a Swedish surname associated with several notable individuals in fields such as music, science, and politics.
  • B. Gotaas-Larsen
    Gotaas-Larsen was a Norwegian shipping company and maritime enterprise that played a key role in the early development of modern cruise operations.
  • C. Krabbé
    Krabbé is a Dutch surname most notably associated with actor and director Jeroen Krabbé.
  • D. Fischmann
    Fischmann is a surname variant of Fishman, typically of Ashkenazi Jewish origin.
  • E. Vogt-Roberts
    Vogt-Roberts is the hyphenated surname of American film director Jordan Vogt-Roberts, known for works like "Kong: Skull Island."
  • 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_69d86dada3808190825d5f80d72fbe88 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1833da68881908710fb2c28e8c6d0 completed April 17, 2026, 12:47 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffdbd5acb48190a10e40074fffd425 completed May 10, 2026, 1:13 a.m.
NEDg Description generation batch_69ffdd527cfc8190a616a2334edffd02 completed May 10, 2026, 1:20 a.m.
NED2 Entity disambiguation (via description) batch_69ffdda1a0908190b7c880c5d66f7400 completed May 10, 2026, 1:21 a.m.
Created at: April 10, 2026, 4:56 a.m.