Triple

T3871155
Position Surface form Disambiguated ID Type / Status
Subject KDKA (AM) E92387 entity
Predicate sisterStation P15137 FINISHED
Object KDKA-FM
KDKA-FM is a Pittsburgh-based commercial radio station known for its sports talk programming and affiliation with major local sports teams.
E396358 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: KDKA-FM | Statement: [KDKA (AM), sisterStation, KDKA-FM]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: KDKA-FM
Context triple: [KDKA (AM), sisterStation, KDKA-FM]
  • A. KDKA (AM)
    KDKA (AM) is a historic Pittsburgh radio station widely recognized as one of the first commercially licensed broadcast stations in the United States.
  • B. WBZ-FM
    WBZ-FM is a Boston-area sports radio station known for its all-sports format and coverage of local professional teams.
  • C. WEEI-FM
    WEEI-FM is a Boston-based sports radio station best known as a flagship broadcaster for Boston Red Sox games and related sports talk programming.
  • D. WBZ (AM)
    WBZ (AM) is a historic Boston-based AM radio station known for its news, talk, and sports programming and status as one of the oldest broadcast stations in the United States.
  • E. WCBS (AM)
    WCBS (AM) is a New York City all-news radio station owned by Audacy, known for its continuous local, national, and international news coverage.
  • 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: KDKA-FM
Triple: [KDKA (AM), sisterStation, KDKA-FM]
Generated description
KDKA-FM is a Pittsburgh-based commercial radio station known for its sports talk programming and affiliation with major local sports teams.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: KDKA-FM
Target entity description: KDKA-FM is a Pittsburgh-based commercial radio station known for its sports talk programming and affiliation with major local sports teams.
  • A. KDKA (AM)
    KDKA (AM) is a historic Pittsburgh radio station widely recognized as one of the first commercially licensed broadcast stations in the United States.
  • B. WBZ-FM
    WBZ-FM is a Boston-area sports radio station known for its all-sports format and coverage of local professional teams.
  • C. WEEI-FM
    WEEI-FM is a Boston-based sports radio station best known as a flagship broadcaster for Boston Red Sox games and related sports talk programming.
  • D. WBZ (AM)
    WBZ (AM) is a historic Boston-based AM radio station known for its news, talk, and sports programming and status as one of the oldest broadcast stations in the United States.
  • E. WCBS (AM)
    WCBS (AM) is a New York City all-news radio station owned by Audacy, known for its continuous local, national, and international news coverage.
  • 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_69aed967448c819086c4b358d37b25aa completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aeec54b0848190a8d4a0e4df7b6227 completed March 9, 2026, 3:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5124769c081909111b4bcac6baa78 completed March 14, 2026, 7:46 a.m.
NEDg Description generation batch_69b5161242f881908e62d0b7cf8e44b9 completed March 14, 2026, 8:02 a.m.
NED2 Entity disambiguation (via description) batch_69b5167379cc819088b4d20558622948 completed March 14, 2026, 8:04 a.m.
Created at: March 9, 2026, 3:20 p.m.