Triple
T24747970
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maihar gharana |
E619054
|
entity |
| Predicate | hasDiscipleLineage |
P38326
|
FINISHED |
| Object | Annapurna Devi |
—
|
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: Annapurna Devi | Statement: [Maihar gharana, hasDiscipleLineage, Annapurna Devi]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDiscipleLineage Context triple: [Maihar gharana, hasDiscipleLineage, Annapurna Devi]
-
A.
wasDiscipleOf
chosen
Indicates that one entity served as a disciple, student, or follower under the guidance or teaching of another entity.
-
B.
hasPriestlyLineage
Indicates that an entity descends from, or belongs to, a recognized priestly family or hereditary priestly line.
-
C.
hasDisciplesAndFollowersTradition
Indicates that an entity has an associated tradition concerning its disciples and followers, including how they are understood, organized, or transmitted over time.
-
D.
hasMagicLineage
Indicates that one entity is descended from, or ancestrally connected to, another through a bloodline associated with magic or supernatural powers.
-
E.
divineLineage
Indicates that one entity is descended from, or originates from, a divine or god-like being.
- 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_69e2fabb349881908a13a212a0221a63 |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f48b9b687881908fd87a2f5fa0b1e7 |
completed | May 1, 2026, 11:16 a.m. |
| PD | Predicate disambiguation | batch_69f48060597c8190a4414e4e4fcb1fec |
completed | May 1, 2026, 10:28 a.m. |
Created at: April 18, 2026, 4:23 a.m.