Triple

T18702239
Position Surface form Disambiguated ID Type / Status
Subject Carlsson på taket E457280 entity
Predicate associatedWithCharacter P1481 FINISHED
Object Lillebror
Lillebror is the young boy protagonist who befriends the mischievous flying man Karlsson in Astrid Lindgren’s beloved children’s stories.
E1338237 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: Lillebror | Statement: [Carlsson på taket, associatedWithCharacter, Lillebror]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lillebror
Context triple: [Carlsson på taket, associatedWithCharacter, Lillebror]
  • A. Lillestrøm
    Lillestrøm is a Norwegian town and former municipality in the Greater Oslo Region, known as a regional commercial center and transport hub.
  • B. Hellemmes-Lille
    Hellemmes-Lille is a former independent commune now functioning as an associated district of the city of Lille in northern France.
  • C. Mellerud
    Mellerud is a small town in western Sweden known for its location by Lake Vänern and its role as a local service and transport hub.
  • D. Örgryte IS
    Örgryte IS is a Swedish sports club best known for its historic football team, one of the oldest in Sweden, based in Gothenburg.
  • E. Mjøndalen
    Mjøndalen is a town in Viken county, Norway, known historically for its industry and for its football club Mjøndalen IF.
  • 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: Lillebror
Triple: [Carlsson på taket, associatedWithCharacter, Lillebror]
Generated description
Lillebror is the young boy protagonist who befriends the mischievous flying man Karlsson in Astrid Lindgren’s beloved children’s stories.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Lillebror
Target entity description: Lillebror is the young boy protagonist who befriends the mischievous flying man Karlsson in Astrid Lindgren’s beloved children’s stories.
  • A. Lillestrøm
    Lillestrøm is a Norwegian town and former municipality in the Greater Oslo Region, known as a regional commercial center and transport hub.
  • B. Hellemmes-Lille
    Hellemmes-Lille is a former independent commune now functioning as an associated district of the city of Lille in northern France.
  • C. Mellerud
    Mellerud is a small town in western Sweden known for its location by Lake Vänern and its role as a local service and transport hub.
  • D. Örgryte IS
    Örgryte IS is a Swedish sports club best known for its historic football team, one of the oldest in Sweden, based in Gothenburg.
  • E. Mjøndalen
    Mjøndalen is a town in Viken county, Norway, known historically for its industry and for its football club Mjøndalen IF.
  • 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_69d8d392aad081909fe31aa03e6e97d1 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e56714d0588190ac050356bc2784fd completed April 19, 2026, 11:36 p.m.
NED1 Entity disambiguation (via context triple) batch_6a052b36caa88190a6302741aca9eb00 completed May 14, 2026, 1:53 a.m.
NEDg Description generation batch_6a052bb371b88190a632f39c891df93b completed May 14, 2026, 1:56 a.m.
NED2 Entity disambiguation (via description) batch_6a052c7532588190bcc3e2f15fef253a completed May 14, 2026, 1:59 a.m.
Created at: April 10, 2026, 11:49 a.m.