Triple

T16781022
Position Surface form Disambiguated ID Type / Status
Subject Harold Finch E407855 entity
Predicate enemyOf P437 FINISHED
Object Decima Technologies E1168894 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: Decima Technologies | Statement: [Harold Finch, enemyOf, Decima Technologies]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Decima Technologies
Context triple: [Harold Finch, enemyOf, Decima Technologies]
  • A. Decima Technologies chosen
    Decima Technologies is a clandestine, highly advanced artificial intelligence–driven organization in the TV series "Person of Interest," known for its ruthless pursuit of mass surveillance and control.
  • B. Quasar Technologies
    Quasar Technologies is the company that originally developed the Qt application development framework, widely used for creating cross-platform software.
  • C. Vandelay Technologies
    Vandelay Technologies is a powerful, futuristic tech megacorporation serving as the primary villainous company in the rhythm-action video game Hi-Fi Rush.
  • D. Amoeba Technologies
    Amoeba Technologies is a technology company whose board has included noted innovation and organizational learning expert John Seely Brown.
  • E. Nisum Technologies
    Nisum Technologies is a global technology consulting and software development firm specializing in digital transformation, e-commerce, and enterprise solutions for large and mid-sized businesses.
  • 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_69d8839270588190886720d9519bbf8f completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3b216726881908ddc9cdc772cd5e4 completed April 18, 2026, 4:32 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00ab0300e48190ad088cd11098ca34 completed May 10, 2026, 3:57 p.m.
Created at: April 10, 2026, 5:22 a.m.