Triple

T9400354
Position Surface form Disambiguated ID Type / Status
Subject T-1000 E226450 entity
Predicate enemy P4567 FINISHED
Object T-800 E388285 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: T-800 | Statement: [T-1000, enemy, T-800]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: T-800
Context triple: [T-1000, enemy, T-800]
  • A. T-800 chosen
    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.
  • B. T-1000
    The T-1000 is a shape-shifting, liquid-metal assassin android and primary antagonist in the film "Terminator 2: Judgment Day."
  • C. T1000 train
    The T1000 train is an earlier generation of electric multiple unit rolling stock used on the Oslo Metro system in Norway.
  • D. Kyle Reese
    Kyle Reese is a time-traveling resistance fighter from the Terminator franchise, best known as John Connor’s father and protector of Sarah Connor against Skynet’s machines.
  • E. Prototype Series 1000 Terminator
    The Prototype Series 1000 Terminator is a highly advanced, shape-shifting liquid metal assassin android from the Terminator science fiction franchise.
  • 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_69ca843170f88190800a8ab2b5fc568e completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd5156b9588190bafb6b1c3ee3c0ed completed April 1, 2026, 5:09 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1079798048190a1bd5318df4b1649 completed April 4, 2026, 12:44 p.m.
Created at: March 30, 2026, 7:46 p.m.