Triple

T4548314
Position Surface form Disambiguated ID Type / Status
Subject Swiss Broadcasting Corporation E110097 entity
Predicate hasDivision P35 FINISHED
Object SRF
SRF is the German-language division of the Swiss Broadcasting Corporation, responsible for producing and broadcasting radio, television, and online content in German-speaking Switzerland.
 E452047 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: SRF | Statement: [Swiss Broadcasting Corporation, hasDivision, SRF]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SRF
Context triple: [Swiss Broadcasting Corporation, hasDivision, SRF]
  • A. SRF
    SRF is a French filmmakers' association best known for organizing the Directors' Fortnight sidebar at the Cannes Film Festival and advocating for directors' artistic and professional interests.
  • B. SRFC
    SRFC is the commonly used abbreviation for Sacramento Republic FC, a professional soccer club based in Sacramento, California.
  • C. SFR
    SFR is a major French telecommunications company providing mobile, internet, and television services.
  • D. SRG
    SRG is the IATA airport code for Jenderal Ahmad Yani International Airport serving Semarang, Indonesia.
  • E. SRB
    SRB is the commonly used abbreviation for Sveriges Riksbank, the central bank of Sweden and the world’s oldest central bank.
  • 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: SRF
Triple: [Swiss Broadcasting Corporation, hasDivision, SRF]
Generated description
SRF is the German-language division of the Swiss Broadcasting Corporation, responsible for producing and broadcasting radio, television, and online content in German-speaking Switzerland.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SRF
Target entity description: SRF is the German-language division of the Swiss Broadcasting Corporation, responsible for producing and broadcasting radio, television, and online content in German-speaking Switzerland.
  • A. SRF
    SRF is a French filmmakers' association best known for organizing the Directors' Fortnight sidebar at the Cannes Film Festival and advocating for directors' artistic and professional interests.
  • B. SRFC
    SRFC is the commonly used abbreviation for Sacramento Republic FC, a professional soccer club based in Sacramento, California.
  • C. SFR
    SFR is a major French telecommunications company providing mobile, internet, and television services.
  • D. SRG
    SRG is the IATA airport code for Jenderal Ahmad Yani International Airport serving Semarang, Indonesia.
  • E. SRB
    SRB is the commonly used abbreviation for Sveriges Riksbank, the central bank of Sweden and the world’s oldest central bank.
  • 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_69bd4412524c8190be5bcc9ddee91848 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd57f272248190983ae439bd0ac0cc completed March 20, 2026, 2:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69bdb945bd3881908e6c3f5f91b5f38e completed March 20, 2026, 9:16 p.m.
NEDg Description generation batch_69bdbecf94d0819087519e44aab5a035 completed March 20, 2026, 9:40 p.m.
NED2 Entity disambiguation (via description) batch_69bdbf81f1208190946611fb6a1c20ba completed March 20, 2026, 9:43 p.m.
Created at: March 20, 2026, 1:05 p.m.