Triple
T2601001
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maitreya |
E58341
|
entity |
| Predicate | willTeach |
P25982
|
FINISHED |
| Object | Pure dharma after it has disappeared |
—
|
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: Pure dharma after it has disappeared | Statement: [Maitreya, willTeach, Pure dharma after it has disappeared]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: willTeach Context triple: [Maitreya, willTeach, Pure dharma after it has disappeared]
-
A.
hasTeaching
chosen
Indicates that one entity provides instruction or educational guidance to another entity.
-
B.
isTaughtAs
Indicates that something is presented or delivered as instructional content, typically within an educational or training context.
-
C.
hasTeachingRole
Indicates that one entity holds a position or responsibility involving teaching or instruction in relation to another entity.
-
D.
taughtAs
Indicates that one entity served as a teacher or instructor for another entity in an educational or training context.
-
E.
typeOfTeaching
Indicates the specific method or style of teaching used in an instructional context.
- 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_69ab4ac14040819098b13f4a27d5c8ff |
completed | March 6, 2026, 9:44 p.m. |
| NER | Named-entity recognition | batch_69abd4587014819089f78e93adf2144c |
completed | March 7, 2026, 7:31 a.m. |
| PD | Predicate disambiguation | batch_69abd0d4e8648190b612eb09aa085451 |
completed | March 7, 2026, 7:16 a.m. |
Created at: March 6, 2026, 9:49 p.m.