Triple

T18009482
Position Surface form Disambiguated ID Type / Status
Subject T2 E430838 entity
Predicate character P662 FINISHED
Object T-1000 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: T-1000 | Statement: [T2, character, T-1000]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: T-1000
Context triple: [T2, character, T-1000]
  • A. T-1000 chosen
    The T-1000 is a shape-shifting, liquid-metal assassin android and primary antagonist in the film "Terminator 2: Judgment Day."
  • B. T-800
    The T-800 is a model of cybernetic assassin and soldier from the Terminator franchise, most famously portrayed by Arnold Schwarzenegger as a time-traveling killer robot with a human appearance.
  • C. Nexus-6 replicant
    A Nexus-6 replicant is a highly advanced, bioengineered android model from the Blade Runner universe, designed to closely mimic humans in appearance and behavior while possessing superior physical capabilities.
  • D. T-X
    The T-X is an advanced, shape-shifting Terminator model from the Terminator franchise, designed as a highly lethal, next-generation assassin android.
  • E. John T. Connor
    John T. Connor was an American businessman and public official who served as U.S. Secretary of Commerce under President Lyndon B. Johnson.
  • 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_69d8b904530081908bf341d842464856 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4b51e13788190bebbbdd7340e0982 completed April 19, 2026, 10:57 a.m.
Created at: April 10, 2026, 10:24 a.m.