Triple

T5138821
Position Surface form Disambiguated ID Type / Status
Subject Danny Baker E115894 entity
Predicate notableWork P4 FINISHED
Object TFI Friday
TFI Friday was a popular, anarchic British television entertainment show of the 1990s known for its live music, celebrity interviews, and chaotic, irreverent style.
E495572 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: TFI Friday | Statement: [Danny Baker, notableWork, TFI Friday]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: TFI Friday
Context triple: [Danny Baker, notableWork, TFI Friday]
  • A. TFI
    TFI is the commonly used abbreviation for the Federal Supreme Court of Switzerland, the country’s highest judicial authority.
  • B. TFI
    TFI is the World Health Organization’s Tobacco Free Initiative, a program dedicated to reducing global tobacco use and its health impacts.
  • C. TFI
    TFI is the stock ticker symbol for the French media conglomerate TF1 Group, which operates television channels and related media services.
  • D. Fridays
    Fridays was a Cartoon Network programming block that showcased new episodes and premieres of the channel’s animated series, typically airing on Friday evenings.
  • E. F.R.I.D.A.Y.
    F.R.I.D.A.Y. is Tony Stark’s advanced artificial intelligence assistant in the Marvel universe, managing his suits, systems, and tactical operations.
  • 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: TFI Friday
Triple: [Danny Baker, notableWork, TFI Friday]
Generated description
TFI Friday was a popular, anarchic British television entertainment show of the 1990s known for its live music, celebrity interviews, and chaotic, irreverent style.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: TFI Friday
Target entity description: TFI Friday was a popular, anarchic British television entertainment show of the 1990s known for its live music, celebrity interviews, and chaotic, irreverent style.
  • A. TFI
    TFI is the commonly used abbreviation for the Federal Supreme Court of Switzerland, the country’s highest judicial authority.
  • B. TFI
    TFI is the World Health Organization’s Tobacco Free Initiative, a program dedicated to reducing global tobacco use and its health impacts.
  • C. TFI
    TFI is the stock ticker symbol for the French media conglomerate TF1 Group, which operates television channels and related media services.
  • D. Fridays
    Fridays was a Cartoon Network programming block that showcased new episodes and premieres of the channel’s animated series, typically airing on Friday evenings.
  • E. F.R.I.D.A.Y.
    F.R.I.D.A.Y. is Tony Stark’s advanced artificial intelligence assistant in the Marvel universe, managing his suits, systems, and tactical operations.
  • 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_69bd44459a988190a772a5c2ec6a1965 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd787acd18819087f09db885893c3e completed March 20, 2026, 4:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69bec4d342c8819088f67c01d3769a6d completed March 21, 2026, 4:18 p.m.
NEDg Description generation batch_69bec5867eac819089ee2c5eddc32a4b completed March 21, 2026, 4:21 p.m.
NED2 Entity disambiguation (via description) batch_69bec5eb535c819097deeb331f9f0f4d completed March 21, 2026, 4:23 p.m.
Created at: March 20, 2026, 1:43 p.m.