Triple
T27179800
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bhramaramba Devi Temple |
E683159
|
entity |
| Predicate | associatedFormOfDevi |
P201029
|
FINISHED |
| Object | Parvati |
—
|
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: Parvati | Statement: [Bhramaramba Devi Temple, associatedFormOfDevi, Parvati]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedFormOfDevi Context triple: [Bhramaramba Devi Temple, associatedFormOfDevi, Parvati]
-
A.
associatedFormation
Indicates that one entity is linked or connected to a particular formation, such as a geological, structural, or organizational configuration.
-
B.
relatedForm
Indicates that one entity is an alternative or variant form of another, such as a different spelling, inflection, or closely related lexical form.
-
C.
associatedSin
Indicates a relationship where one entity is linked or connected to a particular sin or wrongful act.
-
D.
associatedWithForm
Indicates a relationship in which something is linked or connected to a particular form, document, or structured representation.
-
E.
corruptedFormOf
Indicates that one form of an expression, word, or name is a distorted, altered, or degraded version derived from another, more original form.
- 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_69eefad086808190ab89816c0c300476 |
completed | April 27, 2026, 5:57 a.m. |
| NER | Named-entity recognition | batch_69ffc3f0b19c8190b5a749bc3cad21dd |
completed | May 9, 2026, 11:32 p.m. |
| PD | Predicate disambiguation | batch_69ffc1b882808190932b2d43ea5537c9 |
completed | May 9, 2026, 11:22 p.m. |
| PDg | Predicate description generation | batch_69ffc3eed97c819085c06ffe3699ff38 |
completed | May 9, 2026, 11:31 p.m. |
Created at: April 27, 2026, 9:27 a.m.