Triple

T4807530
Position Surface form Disambiguated ID Type / Status
Subject On the Beach E106982 entity
Predicate producer P490 FINISHED
Object Mark Harman
Mark Harman is a film producer best known for his work on the post-apocalyptic drama "On the Beach."
 E472232 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 Harman | Statement: [On the Beach, producer, Mark Harman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mark Harman
Context triple: [On the Beach, producer, Mark Harman]
  • A. John Hull
    John Hull was a prominent 17th-century Boston merchant, silversmith, and colonial official best known for serving as the Massachusetts Bay Colony’s mintmaster.
  • B. Gareth Hunt
    Gareth Hunt was a British actor best known for his roles in the television series "The New Avengers" and the sitcom "Side by Side."
  • C. Alan Manning
    Alan Manning is a British labour economist and professor at the London School of Economics, known for his influential research on wage inequality, monopsony in labour markets, and immigration policy.
  • D. Christopher Benchley
    Christopher Benchley is the son of "Jaws" author Peter Benchley and a member of the Benchley family associated with American literature and ocean conservation.
  • E. David Coulson
    David Coulson is a film editor known for his work on feature films such as the drama "North Country."
  • 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 Harman
Triple: [On the Beach, producer, Mark Harman]
Generated description
Mark Harman is a film producer best known for his work on the post-apocalyptic drama "On the Beach."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mark Harman
Target entity description: Mark Harman is a film producer best known for his work on the post-apocalyptic drama "On the Beach."
  • A. John Hull
    John Hull was a prominent 17th-century Boston merchant, silversmith, and colonial official best known for serving as the Massachusetts Bay Colony’s mintmaster.
  • B. Gareth Hunt
    Gareth Hunt was a British actor best known for his roles in the television series "The New Avengers" and the sitcom "Side by Side."
  • C. Alan Manning
    Alan Manning is a British labour economist and professor at the London School of Economics, known for his influential research on wage inequality, monopsony in labour markets, and immigration policy.
  • D. Christopher Benchley
    Christopher Benchley is the son of "Jaws" author Peter Benchley and a member of the Benchley family associated with American literature and ocean conservation.
  • E. David Coulson
    David Coulson is a film editor known for his work on feature films such as the drama "North Country."
  • 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_69bd43f779448190b92885cb70abb6c2 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd6c69099c8190956b6df42bb922c8 completed March 20, 2026, 3:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69be4da2a1808190bd8d0c073e4bad07 completed March 21, 2026, 7:49 a.m.
NEDg Description generation batch_69be4e61a9a8819096e3c4ba7612de85 completed March 21, 2026, 7:53 a.m.
NED2 Entity disambiguation (via description) batch_69be4f0d51ac819097636aaf2429f317 completed March 21, 2026, 7:55 a.m.
Created at: March 20, 2026, 1:23 p.m.