Triple

T9455355
Position Surface form Disambiguated ID Type / Status
Subject Speaker of the Riksdag E228000 entity
Predicate hasStyle P1609 FINISHED
Object Fru talman
Fru talman is the formal Swedish address used when speaking to a female Speaker of the Riksdag, Sweden’s national parliament.
E801001 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: Fru talman | Statement: [Speaker of the Riksdag, hasStyle, Fru talman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fru talman
Context triple: [Speaker of the Riksdag, hasStyle, Fru talman]
  • A. Tále
    Tále is a popular ski resort and recreational area in the Low Tatras mountains of central Slovakia, known for its slopes, golf course, and year-round outdoor activities.
  • B. Tullistes
    Tullistes are the inhabitants of the French city of Tulle, located in the Corrèze department in central France.
  • C. Faydi
    Faydi is a village located within the Shekhan District in the Kurdistan Region of northern Iraq.
  • D. Frady
    Frady is a surname most notably associated with Claudette Frady, the first wife of musician Roy Orbison.
  • E. Folmar
    Folmar is a masculine given name of Scandinavian origin, most notably borne by the Danish-American film editor Folmar Blangsted.
  • 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: Fru talman
Triple: [Speaker of the Riksdag, hasStyle, Fru talman]
Generated description
Fru talman is the formal Swedish address used when speaking to a female Speaker of the Riksdag, Sweden’s national parliament.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Fru talman
Target entity description: Fru talman is the formal Swedish address used when speaking to a female Speaker of the Riksdag, Sweden’s national parliament.
  • A. Tále
    Tále is a popular ski resort and recreational area in the Low Tatras mountains of central Slovakia, known for its slopes, golf course, and year-round outdoor activities.
  • B. Tullistes
    Tullistes are the inhabitants of the French city of Tulle, located in the Corrèze department in central France.
  • C. Faydi
    Faydi is a village located within the Shekhan District in the Kurdistan Region of northern Iraq.
  • D. Frady
    Frady is a surname most notably associated with Claudette Frady, the first wife of musician Roy Orbison.
  • E. Folmar
    Folmar is a masculine given name of Scandinavian origin, most notably borne by the Danish-American film editor Folmar Blangsted.
  • 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_69ca843b123881909b0e60028475d12d completed March 30, 2026, 2:10 p.m.
NER Named-entity recognition batch_69cd7f8e2c388190a4c5ee6e6d5f2585 completed April 1, 2026, 8:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69d122849fec81908a8e7363d6bab4ed completed April 4, 2026, 2:39 p.m.
NEDg Description generation batch_69d123f710988190a876fab3a1e226d3 completed April 4, 2026, 2:45 p.m.
NED2 Entity disambiguation (via description) batch_69d1252cd7508190a7d11fce51960290 completed April 4, 2026, 2:50 p.m.
Created at: March 30, 2026, 7:52 p.m.