Triple

T7536435
Position Surface form Disambiguated ID Type / Status
Subject WGBH Boston E178162 entity
Predicate networkAffiliation P12340 FINISHED
Object PRI
PRI (Public Radio International) was a major American public radio network known for distributing innovative news, talk, and cultural programming to public radio stations across the United States.
E621602 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: PRI | Statement: [WGBH Boston, networkAffiliation, PRI]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: PRI
Context triple: [WGBH Boston, networkAffiliation, PRI]
  • A. PRI
    PRI is a major Mexican political party that dominated the country’s politics for much of the 20th century.
  • B. pir
    A pir is a spiritual guide or master in Sufism who leads and mentors disciples on the mystical path to closeness with God.
  • C. PREC
    PREC is the Portuguese acronym for the Processo Revolucionário em Curso, the turbulent revolutionary period following Portugal’s 1974 Carnation Revolution marked by intense political and social transformation.
  • D. PI
    PI is the vehicle registration code used on license plates for the district of Pinneberg in the German state of Schleswig-Holstein.
  • E. PI
    PI is a leading independent research institute in Waterloo, Canada, dedicated to advancing fundamental theoretical physics and fostering scientific collaboration and education.
  • 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: PRI
Triple: [WGBH Boston, networkAffiliation, PRI]
Generated description
PRI (Public Radio International) was a major American public radio network known for distributing innovative news, talk, and cultural programming to public radio stations across the United States.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: PRI
Target entity description: PRI (Public Radio International) was a major American public radio network known for distributing innovative news, talk, and cultural programming to public radio stations across the United States.
  • A. PRI chosen
    PRI is a major Mexican political party that dominated the country’s politics for much of the 20th century.
  • B. pir
    A pir is a spiritual guide or master in Sufism who leads and mentors disciples on the mystical path to closeness with God.
  • C. PREC
    PREC is the Portuguese acronym for the Processo Revolucionário em Curso, the turbulent revolutionary period following Portugal’s 1974 Carnation Revolution marked by intense political and social transformation.
  • D. PI
    PI is the vehicle registration code used on license plates for the district of Pinneberg in the German state of Schleswig-Holstein.
  • E. PI
    PI is a leading independent research institute in Waterloo, Canada, dedicated to advancing fundamental theoretical physics and fostering scientific collaboration and education.
  • F. None of above.

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_69c69f2acdbc8190b5a8320168c1d0ba completed March 27, 2026, 3:15 p.m.
NER Named-entity recognition batch_69c6f84db0c48190b2b3d8c5f802f713 completed March 27, 2026, 9:36 p.m.
NED1 Entity disambiguation (via context triple) batch_69c84f0c02148190bb5f63cf9891ec0c completed March 28, 2026, 9:58 p.m.
NEDg Description generation batch_69c84f9ce82081908813a1185b9b3570 completed March 28, 2026, 10:01 p.m.
NED2 Entity disambiguation (via description) batch_69c8500e64788190b196988290aea7d7 completed March 28, 2026, 10:02 p.m.
Created at: March 27, 2026, 3:48 p.m.