Triple

T2602347
Position Surface form Disambiguated ID Type / Status
Subject 1979 NBA Finals E58372 entity
Predicate MVP P2630 FINISHED
Object Frank Oleynick
Frank Oleynick is a former American professional basketball player who played as a guard in the NBA during the 1970s.
 E386559 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: Frank Oleynick | Statement: [1979 NBA Finals, MVP, Frank Oleynick]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Frank Oleynick
Context triple: [1979 NBA Finals, MVP, Frank Oleynick]
  • A. Fred Schuler
    Fred Schuler is a cinematographer best known for his work on films such as the 1980 comedy "Stir Crazy."
  • B. Joseph Buloff
    Joseph Buloff was a Lithuanian-born American actor and director known for his work in Yiddish theater and on Broadway.
  • C. Stephen McFeely
    Stephen McFeely is an American screenwriter best known for co-writing several major Marvel Cinematic Universe films, including the Captain America trilogy and Avengers: Infinity War and Endgame.
  • D. Charles Begole
    Charles Begole was an American mountaineer best known as one of the first climbers to reach the summit of Mount Whitney in the 19th century.
  • E. Ed Hartnett
    Ed Hartnett is an American software developer best known as the creator and primary maintainer of the NetCDF-4 library widely used in scientific computing and data analysis.
  • 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: Frank Oleynick
Triple: [1979 NBA Finals, MVP, Frank Oleynick]
Generated description
Frank Oleynick is a former American professional basketball player who played as a guard in the NBA during the 1970s.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Frank Oleynick
Target entity description: Frank Oleynick is a former American professional basketball player who played as a guard in the NBA during the 1970s.
  • A. Fred Schuler
    Fred Schuler is a cinematographer best known for his work on films such as the 1980 comedy "Stir Crazy."
  • B. Joseph Buloff
    Joseph Buloff was a Lithuanian-born American actor and director known for his work in Yiddish theater and on Broadway.
  • C. Stephen McFeely
    Stephen McFeely is an American screenwriter best known for co-writing several major Marvel Cinematic Universe films, including the Captain America trilogy and Avengers: Infinity War and Endgame.
  • D. Charles Begole
    Charles Begole was an American mountaineer best known as one of the first climbers to reach the summit of Mount Whitney in the 19th century.
  • E. Ed Hartnett
    Ed Hartnett is an American software developer best known as the creator and primary maintainer of the NetCDF-4 library widely used in scientific computing and data analysis.
  • 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_69ab4ac14040819098b13f4a27d5c8ff completed March 6, 2026, 9:44 p.m.
NER Named-entity recognition batch_69abd459ca6c81908505be96d097b739 completed March 7, 2026, 7:31 a.m.
NED1 Entity disambiguation (via context triple) batch_69b4e4c13494819095821f44916329c9 completed March 14, 2026, 4:32 a.m.
NEDg Description generation batch_69b4e88d88248190a4061327296818c7 completed March 14, 2026, 4:48 a.m.
NED2 Entity disambiguation (via description) batch_69b4e8f38ba88190944236b2e8ae743e completed March 14, 2026, 4:49 a.m.
Created at: March 6, 2026, 9:49 p.m.