Triple
T25119861
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tarascan priesthood |
E629235
|
entity |
| Predicate | oversawCultOf |
P144854
|
FINISHED |
| Object | Purépecha patron deities |
—
|
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: Purépecha patron deities | Statement: [Tarascan priesthood, oversawCultOf, Purépecha patron deities]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: oversawCultOf Context triple: [Tarascan priesthood, oversawCultOf, Purépecha patron deities]
-
A.
maintainedCultOf
chosen
Indicates that an entity actively upheld, supported, or perpetuated the religious cult or worship tradition associated with another entity.
-
B.
hasCultSince
Indicates that an entity has had an organized group of devoted followers (a cult) continuously since a specified time or date.
-
C.
typeOfCult
Indicates that one entity is a specific kind or category of cult relative to another entity.
-
D.
hasCultPredecessor
Indicates that one cult, tradition, or religious practice is considered to be derived from, influenced by, or historically preceded by another cult.
-
E.
oversawUnitThatBecame
Indicates that one entity supervised or managed a unit that later transformed into, merged into, or was reconstituted as another unit.
- 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_69e2ff3288048190bd82c3b7f7bd0e62 |
completed | April 18, 2026, 3:49 a.m. |
| NER | Named-entity recognition | batch_69f46d3f35848190b56a4373c97a7d64 |
completed | May 1, 2026, 9:07 a.m. |
| PD | Predicate disambiguation | batch_69f4683472ec8190a483b3b8afe71720 |
completed | May 1, 2026, 8:45 a.m. |
Created at: April 18, 2026, 6:27 a.m.