Triple

T3065716
Position Surface form Disambiguated ID Type / Status
Subject Top of the Lake E62099 entity
Predicate composer P1361 FINISHED
Object Mark Bradshaw
Mark Bradshaw is an Australian composer best known for his atmospheric film and television scores, particularly his collaborations with director Jane Campion.
 E412393 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: Mark Bradshaw | Statement: [Top of the Lake, composer, Mark Bradshaw]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mark Bradshaw
Context triple: [Top of the Lake, composer, Mark Bradshaw]
  • A. Michael Bradsell
    Michael Bradsell is a British film editor known for his work on notable films including Kenneth Branagh’s adaptation of "Henry V" (1989).
  • B. Michael Bradsell
    Michael Bradsell is a British science fiction editor best known for his work on the magazine Jabberwocky.
  • C. Keith Fraase
    Keith Fraase is a film editor best known for his work on the movie "Chappaquiddick."
  • D. Bryan Shaw
    Bryan Shaw is an American Major League Baseball relief pitcher known for his durability and heavy workload out of the bullpen, particularly during his tenure with the Cleveland Indians.
  • E. Brant Daugherty
    Brant Daugherty is an American actor known for his roles in television series like "Pretty Little Liars" and films including the "Fifty Shades" franchise.
  • 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: Mark Bradshaw
Triple: [Top of the Lake, composer, Mark Bradshaw]
Generated description
Mark Bradshaw is an Australian composer best known for his atmospheric film and television scores, particularly his collaborations with director Jane Campion.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mark Bradshaw
Target entity description: Mark Bradshaw is an Australian composer best known for his atmospheric film and television scores, particularly his collaborations with director Jane Campion.
  • A. Michael Bradsell
    Michael Bradsell is a British film editor known for his work on notable films including Kenneth Branagh’s adaptation of "Henry V" (1989).
  • B. Michael Bradsell
    Michael Bradsell is a British science fiction editor best known for his work on the magazine Jabberwocky.
  • C. Keith Fraase
    Keith Fraase is a film editor best known for his work on the movie "Chappaquiddick."
  • D. Bryan Shaw
    Bryan Shaw is an American Major League Baseball relief pitcher known for his durability and heavy workload out of the bullpen, particularly during his tenure with the Cleveland Indians.
  • E. Brant Daugherty
    Brant Daugherty is an American actor known for his roles in television series like "Pretty Little Liars" and films including the "Fifty Shades" franchise.
  • 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_69ad85793e5c8190a358049bc4a98d8c completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ada0fc01dc81908fbdf7c1ef73afe4 completed March 8, 2026, 4:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69b56b2755c88190acc9bc70f1f3a53e completed March 14, 2026, 2:05 p.m.
NEDg Description generation batch_69b56c4c41c88190b00ab8fc43686afb completed March 14, 2026, 2:10 p.m.
NED2 Entity disambiguation (via description) batch_69b56cc2ae948190a5e13992626dd547 completed March 14, 2026, 2:12 p.m.
Created at: March 8, 2026, 3:02 p.m.