Triple
T5489015
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Khatri Punjabis |
E123653
|
entity |
| Predicate | varnaAssociation |
P47373
|
FINISHED |
| Object | Kshatriya (claimed) |
—
|
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: Kshatriya (claimed) | Statement: [Khatri Punjabis, varnaAssociation, Kshatriya (claimed)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: varnaAssociation Context triple: [Khatri Punjabis, varnaAssociation, Kshatriya (claimed)]
-
A.
varnaSystem
chosen
Indicates a relationship where individuals or groups are classified according to the traditional hierarchical varna (caste) system.
-
B.
usesVAR
Indicates that one entity makes use of, employs, or utilizes another entity as a variable or resource in performing some function or operation.
-
C.
associatedWithAlvars
Indicates a relationship in which an entity is connected or related in some way to the Alvars (Tamil Vaishnavite poet-saints).
-
D.
divisionAssociation
Indicates an organizational relationship where one entity functions as a division, branch, or sub-unit of another entity.
-
E.
isAssociatedWith
Indicates that there exists a connection, relationship, or involvement between two entities without specifying its exact nature.
- 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_69bd464a2d908190869324ce176779c8 |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd93e5d0f08190a6cc9fc408b7c5bb |
completed | March 20, 2026, 6:37 p.m. |
| PD | Predicate disambiguation | batch_69bd91a73b148190a865243536a4fe76 |
completed | March 20, 2026, 6:27 p.m. |
Created at: March 20, 2026, 2:10 p.m.