Triple
T27060004
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Villa Mariana de Candelaria |
E685014
|
entity |
| Predicate | isMarianTitleOf |
P103067
|
FINISHED |
| Object | Virgin of Candelaria |
—
|
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: Virgin of Candelaria | Statement: [Villa Mariana de Candelaria, isMarianTitleOf, Virgin of Candelaria]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isMarianTitleOf Context triple: [Villa Mariana de Candelaria, isMarianTitleOf, Virgin of Candelaria]
-
A.
isEcclesiasticalTitle
Indicates that the entity functions as a formal religious or church office, rank, or honorific title within an ecclesiastical context.
-
B.
traditionalMarianTitle
chosen
Indicates that the subject is referred to by a traditional honorific or devotional title associated with the Virgin Mary.
-
C.
isTitularChurchTitleOf
Indicates that a given church serves as the official titular church associated with a particular cardinal’s title.
-
D.
ecclesiasticalTitleIncludes
Indicates that one ecclesiastical title contains, subsumes, or incorporates another ecclesiastical title as part of its designation or scope.
-
E.
isRoyalTitle
Indicates that something is a formal title associated with royalty or a royal rank.
- 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_69ef14835fcc81908bd737b4267ae528 |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69f622e3ab7081909692e4857e7d7633 |
completed | May 2, 2026, 4:14 p.m. |
| PD | Predicate disambiguation | batch_69f61b3ee7b08190a0a1bc5d26b757aa |
completed | May 2, 2026, 3:41 p.m. |
Created at: April 27, 2026, 8:20 a.m.