Triple
T4522957
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kubera |
E103309
|
entity |
| Predicate | associatedBeing |
P50545
|
FINISHED |
| Object | yakshas |
—
|
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: yakshas | Statement: [Kubera, associatedBeing, yakshas]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedBeing Context triple: [Kubera, associatedBeing, yakshas]
-
A.
associatedBeings
chosen
Indicates that two or more beings are linked or connected to each other in some relevant way.
-
B.
associatedHeir
Indicates that one entity is designated or recognized as the heir connected to, or inheriting from, another entity.
-
C.
associatedFort
Indicates that one entity is connected or linked to a particular fort, typically as its related or corresponding fortification.
-
D.
associatedWithSee
Indicates a relationship where one entity is contextually or functionally linked to another through the act or concept of seeing or visual observation.
-
E.
associatedCurrent
Indicates a relationship where a particular current is linked or connected to another entity as its relevant or corresponding current.
- 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_69bd43dba59881908cf59b31df8c7ae1 |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd574d7c2481909049955ca47613a6 |
completed | March 20, 2026, 2:18 p.m. |
| PD | Predicate disambiguation | batch_69bd521cf77c819083852de3094d1377 |
completed | March 20, 2026, 1:56 p.m. |
Created at: March 20, 2026, 1:02 p.m.