Triple

T15132718
Position Surface form Disambiguated ID Type / Status
Subject David Frost E361458 entity
Predicate employer P7 FINISHED
Object TV-am
TV-am was a British breakfast television franchise that broadcast on ITV in the 1980s and early 1990s, known for pioneering morning TV programming in the UK.
E1137863 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: TV-am | Statement: [David Frost, employer, TV-am]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: TV-am
Context triple: [David Frost, employer, TV-am]
  • A. TV
    TV is Apple’s media playback and streaming application for watching movies, TV shows, and other video content across Apple devices.
  • B. .tv
    .tv is the country-code top-level domain originally assigned to Tuvalu that has become popular worldwide for websites related to television and video content.
  • C. TVI
    TVI is a major Portuguese television network known for its popular entertainment, news, and drama programming.
  • D. TV1
    TV1 was the original name of SVT1, the primary television channel of Sweden's public broadcaster Sveriges Television.
  • E. TVN
    TVN is Chile's main public television network, known for its nationwide news, entertainment, and cultural programming.
  • 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: TV-am
Triple: [David Frost, employer, TV-am]
Generated description
TV-am was a British breakfast television franchise that broadcast on ITV in the 1980s and early 1990s, known for pioneering morning TV programming in the UK.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: TV-am
Target entity description: TV-am was a British breakfast television franchise that broadcast on ITV in the 1980s and early 1990s, known for pioneering morning TV programming in the UK.
  • A. TV
    TV is Apple’s media playback and streaming application for watching movies, TV shows, and other video content across Apple devices.
  • B. .tv
    .tv is the country-code top-level domain originally assigned to Tuvalu that has become popular worldwide for websites related to television and video content.
  • C. TVI
    TVI is a major Portuguese television network known for its popular entertainment, news, and drama programming.
  • D. TV1
    TV1 was the original name of SVT1, the primary television channel of Sweden's public broadcaster Sveriges Television.
  • E. TVN
    TVN is Chile's main public television network, known for its nationwide news, entertainment, and cultural programming.
  • 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_69d85a06450081909c5a14ea9851a15e completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e005b29a4c819087f8818e3f5788f5 completed April 15, 2026, 9:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69feb7fd3c448190b4b06fdc1ab2c6a7 completed May 9, 2026, 4:28 a.m.
NEDg Description generation batch_69feb8bb774481908272929358817440 completed May 9, 2026, 4:31 a.m.
NED2 Entity disambiguation (via description) batch_69feb9384b4c81909fe80dec3abc1659 completed May 9, 2026, 4:34 a.m.
Created at: April 10, 2026, 3:06 a.m.