Triple

T18334037
Position Surface form Disambiguated ID Type / Status
Subject Jenny Matrix E439220 entity
Predicate fictionalFather P34570 FINISHED
Object John Matrix 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: John Matrix | Statement: [Jenny Matrix, fictionalFather, John Matrix]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Matrix
Context triple: [Jenny Matrix, fictionalFather, John Matrix]
  • A. John Matrix chosen
    John Matrix is the tough, resourceful former Special Forces colonel portrayed by Arnold Schwarzenegger in the 1985 action film "Commando."
  • B. Karras
    Karras is a surname most notably associated with Alex Karras, an American football player, actor, and sports commentator.
  • C. Korben Dallas
    Korben Dallas is the gruff yet heroic former special forces major-turned-taxi driver who becomes humanity’s reluctant savior in the sci-fi film "The Fifth Element."
  • D. Johnny Cage
    Johnny Cage is a cocky Hollywood action movie star and skilled martial artist known for his flashy moves and comic relief role in the Mortal Kombat fighting game series.
  • E. John Shaft
    John Shaft is a tough, streetwise New York City detective and iconic blaxploitation hero known for his cool demeanor and relentless pursuit of justice.
  • 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_69d8b9175fec8190af865699b4e64d8c completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e50ecbc76c8190a80c0c8c8bce1cbd completed April 19, 2026, 5:20 p.m.
Created at: April 10, 2026, 10:36 a.m.