Triple

T12683528
Position Surface form Disambiguated ID Type / Status
Subject Hesher E303006 entity
Predicate producer P490 FINISHED
Object Robyn Kershaw
Robyn Kershaw is an Australian film and television producer known for backing distinctive independent projects and supporting emerging talent.
E1013685 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: Robyn Kershaw | Statement: [Hesher, producer, Robyn Kershaw]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Robyn Kershaw
Context triple: [Hesher, producer, Robyn Kershaw]
  • A. Lynda Rooke
    Lynda Rooke is a British actress known for her work in film, television, and theatre.
  • B. Kirsten Sheridan
    Kirsten Sheridan is an Irish film director and screenwriter known for character-driven dramas such as "August Rush" and "Disco Pigs."
  • C. Kerri Gowler
    Kerri Gowler is a New Zealand rower and Olympic champion known for her success in women's pair and eight events on the world stage.
  • D. Tessa Wheeler
    Tessa Wheeler was a pioneering early 20th-century British archaeologist known for her influential excavations and contributions to developing modern archaeological methods.
  • E. Leah Haywood
    Leah Haywood is an Australian singer-songwriter and producer known for both her own pop releases and her songwriting work for major international artists.
  • 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: Robyn Kershaw
Triple: [Hesher, producer, Robyn Kershaw]
Generated description
Robyn Kershaw is an Australian film and television producer known for backing distinctive independent projects and supporting emerging talent.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Robyn Kershaw
Target entity description: Robyn Kershaw is an Australian film and television producer known for backing distinctive independent projects and supporting emerging talent.
  • A. Lynda Rooke
    Lynda Rooke is a British actress known for her work in film, television, and theatre.
  • B. Kirsten Sheridan
    Kirsten Sheridan is an Irish film director and screenwriter known for character-driven dramas such as "August Rush" and "Disco Pigs."
  • C. Kerri Gowler
    Kerri Gowler is a New Zealand rower and Olympic champion known for her success in women's pair and eight events on the world stage.
  • D. Tessa Wheeler
    Tessa Wheeler was a pioneering early 20th-century British archaeologist known for her influential excavations and contributions to developing modern archaeological methods.
  • E. Leah Haywood
    Leah Haywood is an Australian singer-songwriter and producer known for both her own pop releases and her songwriting work for major international artists.
  • 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_69d7bdee64a08190801c6d470aefd723 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d961d68358819095bdaab8adf1dcf0 completed April 10, 2026, 8:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6b8c37eb08190a4c15cb50f84c341 completed May 3, 2026, 2:53 a.m.
NEDg Description generation batch_69f6bafee83c819096469034ca32ff7d completed May 3, 2026, 3:03 a.m.
NED2 Entity disambiguation (via description) batch_69f6bb7a0ae08190813411fa677430aa completed May 3, 2026, 3:05 a.m.
Created at: April 9, 2026, 5:21 p.m.