Triple

T5072085
Position Surface form Disambiguated ID Type / Status
Subject Mad Max E114304 entity
Predicate director P255 FINISHED
Object George Miller E128297 NE FINISHED

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: George Miller | Statement: [Mad Max, director, George Miller]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: George Miller
Context triple: [Mad Max, director, George Miller]
  • A. George Miller chosen
    George Miller is an acclaimed Australian filmmaker best known for creating and directing the Mad Max film series and other critically lauded works across genres.
  • B. George Miller
    George Miller is a key architect and partner at the prominent international architecture firm Pei Cobb Freed & Partners.
  • C. Michael Phillip Anderson
    Michael Phillip Anderson was a United States Air Force officer and NASA astronaut who served as a mission specialist on the Space Shuttle Columbia and died in the 2003 Columbia disaster.
  • D. Peter Weir
    Peter Weir is an acclaimed Australian film director known for influential works such as "Picnic at Hanging Rock," "Dead Poets Society," and "The Truman Show."
  • E. Fred Schepisi
    Fred Schepisi is an acclaimed Australian film director and screenwriter known for works such as "The Chant of Jimmie Blacksmith," "A Cry in the Dark," and "Roxanne."
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69bd443cf28c8190ad371d603563dbdd completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd74ce140881909a2874663244c0db completed March 20, 2026, 4:24 p.m.
NED1 Entity disambiguation (via context triple) batch_69beba689ee081909a6bb75c6da07db5 completed March 21, 2026, 3:34 p.m.
Created at: March 20, 2026, 1:39 p.m.