Triple
T34866202
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | tumba de Amelia Goyri (La Milagrosa) |
E1005015
|
entity |
| Predicate | tieneTipoDeCulto |
P31473
|
FINISHED |
| Object | culto no oficial |
—
|
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: culto no oficial | Statement: [tumba de Amelia Goyri (La Milagrosa), tieneTipoDeCulto, culto no oficial]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tieneTipoDeCulto Context triple: [tumba de Amelia Goyri (La Milagrosa), tieneTipoDeCulto, culto no oficial]
-
A.
typeOfCult
chosen
Indicates that one entity is a specific kind or category of cult relative to another entity.
-
B.
hasCulticPractice
Indicates that an entity engages in, observes, or is associated with a specific religious or ritualistic practice.
-
C.
typeOfCultObject
Indicates that one entity is the specific kind or category of cult object to which the other entity belongs or is classified.
-
D.
hasMysteryCult
Indicates that an entity is associated with, participates in, or possesses a mystery cult, typically involving secret or esoteric religious practices.
-
E.
hasCulticViolation
Indicates that an entity is involved in or responsible for a breach of established religious or cultic rules, rituals, or sacred obligations.
- 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_69f76dbb678081909a247b9b5e1a73ac |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f7979a073881909a4fde2558e6b6f3 |
completed | May 3, 2026, 6:44 p.m. |
| PD | Predicate disambiguation | batch_69f7961550f88190b7bb8a9155458b54 |
completed | May 3, 2026, 6:38 p.m. |
Created at: May 3, 2026, 4 p.m.