Triple

T11294520
Position Surface form Disambiguated ID Type / Status
Subject Danish trade unions E267415 entity
Predicate include P1393 FINISHED
Object Djøf
Djøf is a Danish professional organization and trade union representing academics and professionals in law, economics, political science, and related social sciences.
 E917697 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: Djøf | Statement: [Danish trade unions, include, Djøf]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Djøf
Context triple: [Danish trade unions, include, Djøf]
  • A. Lessebo
    Lessebo is a small locality and municipality in southern Sweden known for its traditional paper mill and glassmaking heritage.
  • B. Tjøme
    Tjøme is a scenic island and former municipality in Vestfold, Norway, known for its coastal landscapes, summer cabins, and popular seaside recreation areas.
  • C. Tjuneroy
    Tjuneroy was an ancient Egyptian official, likely a high-ranking scribe or priest under Ramesses II, associated with the creation of the Saqqara King List.
  • D. Bjerke
    Bjerke is a neighborhood in the Bjerke borough of Oslo, Norway, known primarily as a residential area with local services and amenities.
  • E. Dæhlie
    Dæhlie is a Norwegian surname most famously associated with legendary cross-country skier Bjørn Dæhlie.
  • 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: Djøf
Triple: [Danish trade unions, include, Djøf]
Generated description
Djøf is a Danish professional organization and trade union representing academics and professionals in law, economics, political science, and related social sciences.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Djøf
Target entity description: Djøf is a Danish professional organization and trade union representing academics and professionals in law, economics, political science, and related social sciences.
  • A. Lessebo
    Lessebo is a small locality and municipality in southern Sweden known for its traditional paper mill and glassmaking heritage.
  • B. Tjøme
    Tjøme is a scenic island and former municipality in Vestfold, Norway, known for its coastal landscapes, summer cabins, and popular seaside recreation areas.
  • C. Tjuneroy
    Tjuneroy was an ancient Egyptian official, likely a high-ranking scribe or priest under Ramesses II, associated with the creation of the Saqqara King List.
  • D. Bjerke
    Bjerke is a neighborhood in the Bjerke borough of Oslo, Norway, known primarily as a residential area with local services and amenities.
  • E. Dæhlie
    Dæhlie is a Norwegian surname most famously associated with legendary cross-country skier Bjørn Dæhlie.
  • 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_69d6aac993a08190a6f36445ebaf9a43 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7e98b149481909f432a6b9ef8bfbb completed April 9, 2026, 6:01 p.m.
NED1 Entity disambiguation (via context triple) batch_69e50a32ac308190828e1138522527fb completed April 19, 2026, 5 p.m.
NEDg Description generation batch_69e510f9edb4819097e9fa1ce85504ed completed April 19, 2026, 5:29 p.m.
NED2 Entity disambiguation (via description) batch_69e516ac8dec81909c9c1eece372189e completed April 19, 2026, 5:53 p.m.
Created at: April 8, 2026, 9:32 p.m.