Triple
T30584199
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kakusandha Buddha |
E778459
|
entity |
| Predicate | chiefFemaleDisciple |
P38326
|
FINISHED |
| Object | Samaṇī |
—
|
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: Samaṇī | Statement: [Kakusandha Buddha, chiefFemaleDisciple, Samaṇī]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: chiefFemaleDisciple Context triple: [Kakusandha Buddha, chiefFemaleDisciple, Samaṇī]
-
A.
wasDiscipleOf
chosen
Indicates that one entity served as a disciple, student, or follower under the guidance or teaching of another entity.
-
B.
chiefMistressOf
Indicates that one person is the primary or most important mistress (non-marital romantic or sexual partner) of another person.
-
C.
chiefQueen
Indicates that one entity is the primary or highest-ranking queen in relation to another entity.
-
D.
spiritualLeaderOf
Indicates that one entity serves as the primary religious or spiritual guide, authority, or mentor for another entity or group.
-
E.
chief
Indicates that one entity holds the highest-ranking leadership or authoritative position over another entity or within a specified 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_69f224a04b248190b0ca443ec86207b8 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f68a16debc8190a12f5f65ced055d7 |
completed | May 2, 2026, 11:34 p.m. |
| PD | Predicate disambiguation | batch_69f6860def1c81909d79e1f088c4b5e5 |
completed | May 2, 2026, 11:17 p.m. |
Created at: April 29, 2026, 8:23 p.m.