Triple
T33969470
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chapel of Grace |
E870949
|
entity |
| Predicate | hasNotableDevotionType |
P199221
|
FINISHED |
| Object | Marian devotion |
—
|
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: Marian devotion | Statement: [Chapel of Grace, hasNotableDevotionType, Marian devotion]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNotableDevotionType Context triple: [Chapel of Grace, hasNotableDevotionType, Marian devotion]
-
A.
hasDevoteeType
Indicates that an entity has a devotee characterized by a specific type or category of devotion.
-
B.
hasLiturgicalDevotionType
chosen
Indicates a relationship in which a religious practice, observance, or devotion is associated with a specific type or form of liturgical devotion.
-
C.
hasDevotionalRole
Indicates that an entity holds or performs a specific role or function within a devotional or religious practice.
-
D.
isDevotedTo
Indicates a strong, enduring commitment or dedication that one entity directs toward another.
-
E.
hasHolinessType
Indicates a relationship where an entity is assigned or associated with a specific type or category of holiness.
- 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_69f3499ce8e88190b66e1d49ad8c7037 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_6a022c5269888190944314074aedfe73 |
completed | May 11, 2026, 7:21 p.m. |
| PD | Predicate disambiguation | batch_6a02286020308190b238183f7ba2065f |
completed | May 11, 2026, 7:05 p.m. |
Created at: May 1, 2026, 1:50 a.m.