Triple

T19619844
Position Surface form Disambiguated ID Type / Status
Subject Bergens E470972 entity
Predicate primaryRoleInTrolls P58016 FINISHED
Object main antagonists LITERAL 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: main antagonists | Statement: [Bergens, primaryRoleInTrolls, main antagonists]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: primaryRoleInTrolls
Context triple: [Bergens, primaryRoleInTrolls, main antagonists]
  • A. themeRole
    Indicates that an entity is the primary participant undergoing or affected by the action or event expressed by a predicate.
  • B. primaryRoleOnLine
    Indicates that an entity serves as the main or most important role associated with a particular line (such as a transit line, product line, or communication line).
  • C. roleInHorribleBosses
    Indicates that an entity has a specific acting role or character appearance in the movie "Horrible Bosses."
  • D. roleInTauris
    Indicates that an entity has a specific role or function within the context of Tauris (e.g., a work, setting, or domain associated with Tauris).
  • E. primaryAntagonistType chosen
    Indicates the role or category of the main opposing force or adversary that serves as the central source of conflict.
  • F. None of above.

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_69d8e510fa248190b7afb274a1d4cf73 completed April 10, 2026, 11:54 a.m.
NER Named-entity recognition batch_69e640e512d08190a76bf81b3282e0e5 completed April 20, 2026, 3:06 p.m.
PD Predicate disambiguation batch_69e514e5cb108190ae260e466c447314 completed April 19, 2026, 5:46 p.m.
Created at: April 10, 2026, 1:43 p.m.