Triple
T17939004
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Karva Chauth |
E448538
|
entity |
| Predicate | modernVariation |
P129793
|
FINISHED |
| Object | some husbands also fast |
—
|
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: some husbands also fast | Statement: [Karva Chauth, modernVariation, some husbands also fast]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: modernVariation Context triple: [Karva Chauth, modernVariation, some husbands also fast]
-
A.
modernUse
Indicates how something is currently used or applied in modern times.
-
B.
modernAccess
Indicates that an entity has contemporary, up-to-date means or methods of accessing or interacting with another entity or resource.
-
C.
modernBase
Indicates that one entity serves as the contemporary or current foundational basis or reference point for another entity.
-
D.
modernRevivalIn
Indicates that something has experienced a renewed or modern resurgence, popularity, or reinterpretation within a specified place, context, or period.
-
E.
modernEquivalent
Indicates that one entity serves as the contemporary or updated counterpart of another earlier or traditional entity.
- F. None of above. chosen
Provenance (4 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_69d8b9f79d14819095540856928f0e25 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4ad9455fc81908bf595f9ed42c624 |
completed | April 19, 2026, 10:25 a.m. |
| PD | Predicate disambiguation | batch_69e3f8e713d481908b4a126258c18b63 |
completed | April 18, 2026, 9:34 p.m. |
| PDg | Predicate description generation | batch_69e42d8d68288190a05dc5d7803cf823 |
completed | April 19, 2026, 1:19 a.m. |
Created at: April 10, 2026, 10:21 a.m.