Triple

T5098491
Position Surface form Disambiguated ID Type / Status
Subject Brunswick Manifesto E114924 entity
Predicate threatenedAction P1358 FINISHED
Object severe reprisals against Paris if the royal family were harmed 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: severe reprisals against Paris if the royal family were harmed | Statement: [Brunswick Manifesto, threatenedAction, severe reprisals against Paris if the royal family were harmed]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: threatenedAction
Context triple: [Brunswick Manifesto, threatenedAction, severe reprisals against Paris if the royal family were harmed]
  • A. threatenedBy
    Indicates that one entity poses a danger or potential harm to another entity.
  • B. threatToHumans
    Indicates that the subject poses or represents a potential danger, harm, or risk to humans.
  • C. threatenedToKill
    Indicates that one entity has made a threat or expressed an intention to kill another entity.
  • D. threat chosen
    Indicates a relationship where one entity expresses or poses potential harm, danger, or negative consequences toward another entity.
  • E. threatType
    Indicates the specific category or nature of a threat that one entity poses or represents in relation to another.
  • 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_69bd443fc49c819089629c00e311310c completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd7567d21081909227ed8f08b74c71 completed March 20, 2026, 4:27 p.m.
PD Predicate disambiguation batch_69bd715e06808190931934dc9930f997 completed March 20, 2026, 4:10 p.m.
Created at: March 20, 2026, 1:40 p.m.