Triple

T1913685
Position Surface form Disambiguated ID Type / Status
Subject Roger Williams E38166 entity
Predicate reasonForBanishment P15406 FINISHED
Object views on religious liberty and separation of church and state 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: views on religious liberty and separation of church and state | Statement: [Roger Williams, reasonForBanishment, views on religious liberty and separation of church and state]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: reasonForBanishment
Context triple: [Roger Williams, reasonForBanishment, views on religious liberty and separation of church and state]
  • A. reasonForBan
    Indicates the justification or cause that led to an entity being banned.
  • B. bannedBy
    Indicates that an entity is prohibited or disallowed as a result of a decision or action taken by another entity.
  • C. causeOfExile chosen
    Indicates the reason or circumstance that led to an entity’s exile.
  • D. reasonForDisqualification
    Indicates the specific cause or justification for which an entity was deemed ineligible or disqualified from consideration or participation.
  • E. reasonForElimination
    Indicates the specific cause or justification for why an entity was removed, disqualified, or excluded from consideration.
  • 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_69a8862a26088190aae5243695aeefc0 completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69abb34d94fc8190a5bf1e582c77c725 completed March 7, 2026, 5:10 a.m.
PD Predicate disambiguation batch_69abafeba3d88190afcce67483d8625b completed March 7, 2026, 4:56 a.m.
Created at: March 4, 2026, 7:35 p.m.