Triple

T4028683
Position Surface form Disambiguated ID Type / Status
Subject The Now Show E83653 entity
Predicate hasCastMember P2308 FINISHED
Object Gemma Arrowsmith
Gemma Arrowsmith is a British comedy writer, performer, and impressionist known for her work on radio and television sketch shows.
E409446 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: Gemma Arrowsmith | Statement: [The Now Show, hasCastMember, Gemma Arrowsmith]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gemma Arrowsmith
Context triple: [The Now Show, hasCastMember, Gemma Arrowsmith]
  • A. Edith Campion
    Edith Campion was a New Zealand actress and co-founder of the New Zealand Players theatre company, known also as the mother of acclaimed film director Jane Campion.
  • B. Lucy Barclay
    Lucy Barclay was the wife of English gun-maker and businessman Samuel Galton Jr., a prominent member of the Lunar Society of Birmingham.
  • C. Sadie Smith
    Sadie Smith is the birth name of Zadie Smith, the acclaimed British novelist known for works such as "White Teeth" and "On Beauty."
  • D. Anne Ashmond
    Anne Ashmond is a fictional character appearing in the film "Royal Wedding."
  • E. Beatrice Dawson
    Beatrice Dawson was a British costume designer known for her work on mid-20th-century films, earning multiple Academy Award nominations for her period and character costumes.
  • 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: Gemma Arrowsmith
Triple: [The Now Show, hasCastMember, Gemma Arrowsmith]
Generated description
Gemma Arrowsmith is a British comedy writer, performer, and impressionist known for her work on radio and television sketch shows.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Gemma Arrowsmith
Target entity description: Gemma Arrowsmith is a British comedy writer, performer, and impressionist known for her work on radio and television sketch shows.
  • A. Edith Campion
    Edith Campion was a New Zealand actress and co-founder of the New Zealand Players theatre company, known also as the mother of acclaimed film director Jane Campion.
  • B. Lucy Barclay
    Lucy Barclay was the wife of English gun-maker and businessman Samuel Galton Jr., a prominent member of the Lunar Society of Birmingham.
  • C. Sadie Smith
    Sadie Smith is the birth name of Zadie Smith, the acclaimed British novelist known for works such as "White Teeth" and "On Beauty."
  • D. Anne Ashmond
    Anne Ashmond is a fictional character appearing in the film "Royal Wedding."
  • E. Beatrice Dawson
    Beatrice Dawson was a British costume designer known for her work on mid-20th-century films, earning multiple Academy Award nominations for her period and character costumes.
  • 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_69aed92e29ac819080f7a98b594fec05 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aefaf066b08190afbb4a18ddc8d67e completed March 9, 2026, 4:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69b556358f148190be7008092d0023af completed March 14, 2026, 12:36 p.m.
NEDg Description generation batch_69b55a5b292481908723530461bad562 completed March 14, 2026, 12:53 p.m.
NED2 Entity disambiguation (via description) batch_69b55ae09ac48190a014aaf5b309e029 completed March 14, 2026, 12:56 p.m.
Created at: March 9, 2026, 3:36 p.m.