Triple
T32212123
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Khaling Rai |
E822835
|
entity |
| Predicate | traditionalRitualSpecialists |
P17182
|
FINISHED |
| Object | Kirati shamans |
—
|
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: Kirati shamans | Statement: [Khaling Rai, traditionalRitualSpecialists, Kirati shamans]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: traditionalRitualSpecialists Context triple: [Khaling Rai, traditionalRitualSpecialists, Kirati shamans]
-
A.
ritualSpecialist
chosen
Indicates that one entity serves as a designated expert or practitioner responsible for performing or overseeing rituals in relation to another entity or context.
-
B.
ritualSpecialization
Indicates a relationship where an entity is specifically focused on, trained in, or primarily responsible for performing a particular type of ritual or set of ritual practices.
-
C.
ritualsDirectedAt
Indicates that certain rituals are performed with a specific entity, object, or target as their intended focus or recipient.
-
D.
ritualTools
Indicates that certain tools or objects are used in the performance or practice of a ritual.
-
E.
ritualCategory
Indicates the classification relationship that assigns a ritual to a specific ritual type or category.
- 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_69f3490a3bec819097bc58d4731b9d08 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69fe9fb9735c8190a360b556c9d00b3f |
completed | May 9, 2026, 2:45 a.m. |
| PD | Predicate disambiguation | batch_69fe9eaa88008190a9b2a469dc685002 |
completed | May 9, 2026, 2:40 a.m. |
Created at: May 1, 2026, 12:37 a.m.