Triple
T4882278
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Angiras sages |
E109356
|
entity |
| Predicate | functionInRitual |
P59587
|
FINISHED |
| Object | officiating priests |
—
|
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: officiating priests | Statement: [Angiras sages, functionInRitual, officiating priests]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: functionInRitual Context triple: [Angiras sages, functionInRitual, officiating priests]
-
A.
hasRitual
Indicates that an entity performs, observes, or is associated with a specific ritual or ceremonial practice.
-
B.
appearsInRitual
Indicates that an entity is included, featured, or participates as a component or element within a specific ritual.
-
C.
hasRitualFocus
Indicates that an entity is associated with or directed toward a particular object, practice, or element that serves as the central focus of a ritual.
-
D.
partOfRitual
Indicates that an action, object, or event is included as a component or step within a larger ritual.
-
E.
relatedRitual
Indicates that one entity is associated with, connected to, or involved in the performance or context of a particular ritual.
- 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_69bd440e9d64819083e82cf33b4d9570 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6dde6fcc8190a5aa7587f85632bd |
completed | March 20, 2026, 3:55 p.m. |
| PD | Predicate disambiguation | batch_69bd6c2be5e881909f6ec9c3bcde49f3 |
completed | March 20, 2026, 3:47 p.m. |
| PDg | Predicate description generation | batch_69bd6d5976a081909090c0c263f6e9b7 |
completed | March 20, 2026, 3:52 p.m. |
Created at: March 20, 2026, 1:27 p.m.