Triple

T913652
Position Surface form Disambiguated ID Type / Status
Subject Girondins E19719 entity
Predicate fateOfLeaders P22875 FINISHED
Object many leaders executed by guillotine in 1793 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: many leaders executed by guillotine in 1793 | Statement: [Girondins, fateOfLeaders, many leaders executed by guillotine in 1793]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: fateOfLeaders
Context triple: [Girondins, fateOfLeaders, many leaders executed by guillotine in 1793]
  • A. militaryLeader
    Indicates that one entity serves as the commanding military leader of another entity, such as a state, organization, or armed force.
  • B. mainLeaders
    Indicates that the referenced entities serve as the primary or most important leaders within a group, organization, or context.
  • C. politicalLeaderBehind
    Indicates that a political leader is the driving force or primary influence behind a particular action, decision, policy, or event.
  • D. belligerentLeader
    Indicates that an entity serves as a leader or authority figure of a party engaged in a conflict, war, or hostile confrontation.
  • E. leaderCapturedAndExecuted
    Indicates that a leader was seized by an opposing force and subsequently put to death as a consequence of that capture.
  • F. None of above. chosen

Provenance (4 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_69a4939f91a08190ba68c2c81eab90fe completed March 1, 2026, 7:29 p.m.
NER Named-entity recognition batch_69a4b6755c488190b7f7848110e3ea2c completed March 1, 2026, 9:58 p.m.
PD Predicate disambiguation batch_69a4b292d3408190947cbc2f794cf8c5 completed March 1, 2026, 9:41 p.m.
PDg Predicate description generation batch_69a4b67499708190a65f24d1fd7e4ec5 completed March 1, 2026, 9:58 p.m.
Created at: March 1, 2026, 7:39 p.m.