Triple
T37213664
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Manganiyar |
E922674
|
entity |
| Predicate | patrons |
P44199
|
FINISHED |
| Object | Rajput communities |
—
|
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: Rajput communities | Statement: [Manganiyar, patrons, Rajput communities]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: patrons Context triple: [Manganiyar, patrons, Rajput communities]
-
A.
coPatron
Indicates a relationship where two or more entities share joint responsibility or role as patrons supporting the same person, group, or endeavor.
-
B.
patronType
Indicates the classification or category of a patron in relation to a service, institution, or resource.
-
C.
laterPatron
Indicates that one entity serves as a patron of another at a later time than some reference patronage relationship.
-
D.
traditionalPatron
chosen
Indicates a relationship where one entity serves as a customary or historically established patron or supporter of another.
-
E.
patron of
Indicates a supportive relationship in which one entity provides sponsorship, protection, or backing to another, often enabling its activities or development.
- 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_69f76ea6f5288190b8d9988f613811c0 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fb9e1845e881908d19158440cf3b87 |
completed | May 6, 2026, 8:01 p.m. |
| PD | Predicate disambiguation | batch_69fb8d08d6988190a00794ac26078348 |
completed | May 6, 2026, 6:48 p.m. |
Created at: May 3, 2026, 4:15 p.m.