Triple
T36373520
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Amritdhari Sikhs |
E895831
|
entity |
| Predicate | vowsAtInitiation |
P61592
|
FINISHED |
| Object | abstain from hair cutting |
—
|
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: abstain from hair cutting | Statement: [Amritdhari Sikhs, vowsAtInitiation, abstain from hair cutting]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: vowsAtInitiation Context triple: [Amritdhari Sikhs, vowsAtInitiation, abstain from hair cutting]
-
A.
vowsAre
Indicates that one entity makes or holds a solemn promise or commitment toward another entity.
-
B.
vowsTo
chosen
Indicates a commitment or solemn promise made by one entity to another to perform, uphold, or refrain from specific actions.
-
C.
vowsRequired
Indicates that a formal promise, oath, or commitment is mandated to proceed with or validate the associated relationship or action.
-
D.
definesVows
Indicates that an entity establishes or specifies the content, terms, or wording of vows for another entity or situation.
-
E.
endsVows
Indicates that one entity terminates or concludes the vows, promises, or commitments associated with another entity.
- 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_69f76e5115588190ad8738860b7bc68b |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7bb3ff1b08190802b1063d55d3923 |
completed | May 3, 2026, 9:16 p.m. |
| PD | Predicate disambiguation | batch_69f7b9a611a081908dd6aec1df3f4d7f |
completed | May 3, 2026, 9:09 p.m. |
Created at: May 3, 2026, 4:10 p.m.