Triple
T10992704
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roman Catholic dioceses |
E259787
|
entity |
| Predicate | hasPrincipalChurch |
P15000
|
FINISHED |
| Object | cathedral |
—
|
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: cathedral | Statement: [Roman Catholic dioceses, hasPrincipalChurch, cathedral]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPrincipalChurch Context triple: [Roman Catholic dioceses, hasPrincipalChurch, cathedral]
-
A.
hasChurch
chosen
Indicates that a place or entity possesses, contains, or is associated with a church.
-
B.
hasParentChurch
Indicates that a church or religious organization is institutionally subordinate to or derived from another church, which serves as its parent or overseeing body.
-
C.
hasChurchType
Indicates that one entity (typically a church) is classified as being of a particular church type or category.
-
D.
isPrincipalPastorOf
Indicates that one entity serves or has served as the main or lead pastor of another entity, typically a church or religious organization.
-
E.
hasClergy
Indicates that an organization or institution possesses or is served by members of the clergy.
- 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_69d6aa8a6a548190a750f944ccdc8064 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d795d32f9081909def643571499521 |
completed | April 9, 2026, 12:04 p.m. |
| PD | Predicate disambiguation | batch_69d72e93ac648190b46c5d12bf3eb1e9 |
completed | April 9, 2026, 4:44 a.m. |
Created at: April 8, 2026, 9:24 p.m.