Triple

T17740303
Position Surface form Disambiguated ID Type / Status
Subject Morton Minsky E442834 entity
Predicate sibling P363 FINISHED
Object Abe Minsky NE NERFINISHED

How this triple was built (2 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: Abe Minsky | Statement: [Morton Minsky, sibling, Abe Minsky]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Abe Minsky
Context triple: [Morton Minsky, sibling, Abe Minsky]
  • A. Morton Minsky chosen
    Morton Minsky was a member of the Minsky family associated with the famous Minsky's Burlesque theater circuit in early 20th-century New York entertainment.
  • B. Marvin Minoff
    Marvin Minoff was an American television and film producer known for his work on socially conscious projects and for co-producing the acclaimed film "Patch Adams."
  • C. Charles Minsky
    Charles Minsky is an American cinematographer known for his work on numerous Hollywood films, particularly romantic comedies.
  • D. Henry Minsky
    Henry Minsky is the son of artificial intelligence pioneer Marvin Minsky and is known as a software engineer and technologist.
  • E. Frank Moses
    Frank Moses is a retired black-ops CIA agent and the main protagonist of the action-comedy film series "RED," known for being reluctantly drawn back into high-stakes espionage.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8b9ed3a2081909b2ec0d4dd2f4c37 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e47acc2610819099451b02bb51891f completed April 19, 2026, 6:48 a.m.
Created at: April 10, 2026, 10:09 a.m.