Triple
T17980063
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dikpalas |
E449576
|
entity |
| Predicate | hasVariantMember |
P72811
|
FINISHED |
| Object | Prajapati |
—
|
NE NERFINISHED |
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: Prajapati | Statement: [Dikpalas, hasVariantMember, Prajapati]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Prajapati Context triple: [Dikpalas, hasVariantMember, Prajapati]
-
A.
Prajapati
Prajapati is a taxonomist credited with formally describing and naming the bacterial order Corynebacteriales.
-
B.
Prajapati
chosen
Prajapati is a Vedic creator deity associated with the origin, ordering, and procreation of the cosmos in early Hindu tradition.
-
C.
Purusha
Purusha is the cosmic being or universal spirit in Vedic and later Hindu philosophy, often depicted as the primordial person whose sacrifice gives rise to the universe and social order.
-
D.
Brahma
Brahma is a large, hardy domestic chicken breed known for its feathered legs, calm temperament, and good meat and egg production.
-
E.
Brahma
Brahma is a popular Brazilian beer brand known for its mass-market lagers and wide distribution across Latin America and beyond.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b9f9927c8190a006110c8b996e61 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4b202aab88190b44851808c75a848 |
completed | April 19, 2026, 10:44 a.m. |
Created at: April 10, 2026, 10:22 a.m.