Triple

T3423897
Position Surface form Disambiguated ID Type / Status
Subject Margaret Kemble Gage E72180 entity
Predicate allegedRole P16813 FINISHED
Object possible informant to American patriots 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: possible informant to American patriots | Statement: [Margaret Kemble Gage, allegedRole, possible informant to American patriots]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: allegedRole
Context triple: [Margaret Kemble Gage, allegedRole, possible informant to American patriots]
  • A. allegedActor
    Indicates that the subject is claimed or accused to be the actor responsible for a particular action or event, without confirming that the claim is true.
  • B. allegedAgentOf
    Indicates that one entity is claimed or suspected, but not confirmed, to be the agent responsible for an action or event involving another entity.
  • C. allegedStatus chosen
    Indicates that a particular status or condition is claimed or asserted about an entity, but has not been confirmed as true.
  • D. allegedImpostor
    Indicates that one entity is claimed or suspected to be fraudulently posing as another entity.
  • E. possibleRole
    Indicates that an entity is capable of or eligible to serve in a particular role or function in a given context.
  • 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_69ad85ad38e48190b7660c5118a35289 completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb9533b588190a18a9b6495712ee0 completed March 8, 2026, 6 p.m.
PD Predicate disambiguation batch_69adadfea024819094b41a13bc004bda completed March 8, 2026, 5:12 p.m.
Created at: March 8, 2026, 3:15 p.m.