Triple

T12401340
Position Surface form Disambiguated ID Type / Status
Subject Saw VI E296258 entity
Predicate portrayedBy P1507 FINISHED
Object Mark Rolston
Mark Rolston is an American character actor known for his intense roles in films such as Aliens, The Shawshank Redemption, and numerous genre and action movies.
E996941 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 Rolston | Statement: [Saw VI, portrayedBy, Mark Rolston]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mark Rolston
Context triple: [Saw VI, portrayedBy, Mark Rolston]
  • A. Matthew Rolston
    Matthew Rolston is an American photographer and director renowned for his stylized celebrity portraiture and visually distinctive music videos.
  • B. Mark Okerstrom
    Mark Okerstrom is a Canadian business executive best known for serving as the former CEO of Expedia Group.
  • C. Matthew Rolph
    Matthew Rolph is an American actor and comedian best known for his marriage to actress and comedian Mary Lynn Rajskub.
  • D. Steve Ralston
    Steve Ralston is a former American soccer midfielder best known as a longtime MLS standout and U.S. national team player, particularly with the New England Revolution.
  • E. Brian M. Stoltz
    Brian M. Stoltz is an American organic chemist known for his work in synthetic methodology and complex natural product synthesis.
  • 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 Rolston
Triple: [Saw VI, portrayedBy, Mark Rolston]
Generated description
Mark Rolston is an American character actor known for his intense roles in films such as Aliens, The Shawshank Redemption, and numerous genre and action movies.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mark Rolston
Target entity description: Mark Rolston is an American character actor known for his intense roles in films such as Aliens, The Shawshank Redemption, and numerous genre and action movies.
  • A. Matthew Rolston
    Matthew Rolston is an American photographer and director renowned for his stylized celebrity portraiture and visually distinctive music videos.
  • B. Mark Okerstrom
    Mark Okerstrom is a Canadian business executive best known for serving as the former CEO of Expedia Group.
  • C. Matthew Rolph
    Matthew Rolph is an American actor and comedian best known for his marriage to actress and comedian Mary Lynn Rajskub.
  • D. Steve Ralston
    Steve Ralston is a former American soccer midfielder best known as a longtime MLS standout and U.S. national team player, particularly with the New England Revolution.
  • E. Brian M. Stoltz
    Brian M. Stoltz is an American organic chemist known for his work in synthetic methodology and complex natural product synthesis.
  • 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_69d6ad9f464c81909db36d7e96e34b9e completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d94d46007c81908e0f4b590402bf58 completed April 10, 2026, 7:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69f671852f588190924ded1c0a360b47 completed May 2, 2026, 9:49 p.m.
NEDg Description generation batch_69f6735b3de08190ab4665206fe71eb4 completed May 2, 2026, 9:57 p.m.
NED2 Entity disambiguation (via description) batch_69f6745a5c148190a76753fdb699706a completed May 2, 2026, 10:02 p.m.
Created at: April 8, 2026, 9:55 p.m.