Triple

T4243339
Position Surface form Disambiguated ID Type / Status
Subject Exile of Napoleon Bonaparte E95466 entity
Predicate hasAlternativeDeathTheory P27547 FINISHED
Object arsenic poisoning 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: arsenic poisoning | Statement: [Exile of Napoleon Bonaparte, hasAlternativeDeathTheory, arsenic poisoning]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasAlternativeDeathTheory
Context triple: [Exile of Napoleon Bonaparte, hasAlternativeDeathTheory, arsenic poisoning]
  • A. hasMannerOfDeath
    Indicates the specific way or circumstances in which an entity died, such as natural causes, accident, homicide, or suicide.
  • B. containsDeathOf
    Indicates that the subject includes, depicts, or involves the death of the referenced entity.
  • C. allegedMannerOfDeath chosen
    Indicates that the specified manner of death is claimed or reported for an entity, but not confirmed as factual.
  • D. discoveredAsDeadBy
    Indicates that one entity was found to be dead by another entity, who discovered their deceased state.
  • E. hasPartInMannerOfDeath
    Indicates that an entity’s involvement in a death is characterized or qualified by a specific manner or way in which the death occurred.
  • 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_69b3453d91548190b4d4ef8fe52aa2ac completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b34e8a676c8190ac2cb59e62613dd9 completed March 12, 2026, 11:38 p.m.
PD Predicate disambiguation batch_69b347f587148190a1830503459939b6 completed March 12, 2026, 11:10 p.m.
Created at: March 12, 2026, 11:05 p.m.