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.