Triple

T3564626
Position Surface form Disambiguated ID Type / Status
Subject Soul Plane E75414 entity
Predicate editor P1954 FINISHED
Object Larry Madaras
Larry Madaras is a film editor best known for his work on the comedy movie "Soul Plane."
 E369342 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: Larry Madaras | Statement: [Soul Plane, editor, Larry Madaras]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Larry Madaras
Context triple: [Soul Plane, editor, Larry Madaras]
  • A. Bernie Kukar
    Bernie Kukar is a former NFL official best known for serving as the referee in multiple Super Bowls during his long officiating career.
  • B. Hans Spialek
    Hans Spialek was a prominent 20th-century Broadway orchestrator and arranger known for his innovative work on numerous classic American musicals.
  • C. Billy Conigliaro
    Billy Conigliaro was an American Major League Baseball outfielder, best known for playing with the Boston Red Sox in the late 1960s and early 1970s.
  • D. Peter Bondra
    Peter Bondra is a Slovak former NHL right winger best known as a prolific goal scorer and franchise star for the Washington Capitals during the 1990s and early 2000s.
  • E. Viktor Knavs
    Viktor Knavs is a Slovenian former car salesman best known as the father of former U.S. First Lady Melania Trump.
  • 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: Larry Madaras
Triple: [Soul Plane, editor, Larry Madaras]
Generated description
Larry Madaras is a film editor best known for his work on the comedy movie "Soul Plane."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Larry Madaras
Target entity description: Larry Madaras is a film editor best known for his work on the comedy movie "Soul Plane."
  • A. Bernie Kukar
    Bernie Kukar is a former NFL official best known for serving as the referee in multiple Super Bowls during his long officiating career.
  • B. Hans Spialek
    Hans Spialek was a prominent 20th-century Broadway orchestrator and arranger known for his innovative work on numerous classic American musicals.
  • C. Billy Conigliaro
    Billy Conigliaro was an American Major League Baseball outfielder, best known for playing with the Boston Red Sox in the late 1960s and early 1970s.
  • D. Peter Bondra
    Peter Bondra is a Slovak former NHL right winger best known as a prolific goal scorer and franchise star for the Washington Capitals during the 1990s and early 2000s.
  • E. Viktor Knavs
    Viktor Knavs is a Slovenian former car salesman best known as the father of former U.S. First Lady Melania Trump.
  • 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_69ad85d512708190829c8b2d3a2ccfb8 completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc0a76c008190a2056b6d990776fe completed March 8, 2026, 6:32 p.m.
NED1 Entity disambiguation (via context triple) batch_69b3bba91d08819081a433c9f06a2c2b completed March 13, 2026, 7:24 a.m.
NEDg Description generation batch_69b3bda1e1ac819094ac613c0e55c048 completed March 13, 2026, 7:32 a.m.
NED2 Entity disambiguation (via description) batch_69b3f5adac0481908b9053585c317be0 completed March 13, 2026, 11:31 a.m.
Created at: March 8, 2026, 3:21 p.m.