Triple

T621076
Position Surface form Disambiguated ID Type / Status
Subject Employment Division v. Smith E14513 entity
Predicate hasFact P8821 FINISHED
Object respondents were members of the Native American Church 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: respondents were members of the Native American Church | Statement: [Employment Division v. Smith, hasFact, respondents were members of the Native American Church]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasFact
Context triple: [Employment Division v. Smith, hasFact, respondents were members of the Native American Church]
  • A. hasLie
    Indicates that an entity is associated with or responsible for a specific lie or false statement.
  • B. hasCase
    Indicates that one entity is involved in, associated with, or characterized by a particular case, instance, or occurrence represented by another entity.
  • C. has
    Indicates that one entity possesses, owns, contains, or includes another entity as part of its state or composition.
  • D. factPattern chosen
    Indicates that a specific configuration of facts or circumstances holds in a situation, typically used as the basis for applying rules, reasoning, or legal/logic inferences.
  • E. hasPar
    Indicates a relationship where one entity has another entity as its parent.
  • 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_69a4934b17c881909ace8270e8ddd202 completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a49e3e5d80819096e72e11b533f931 completed March 1, 2026, 8:14 p.m.
PD Predicate disambiguation batch_69a49cfe9bc081909a01b4b3b48f03b7 completed March 1, 2026, 8:09 p.m.
Created at: March 1, 2026, 7:35 p.m.