Triple
T522713
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Province VI |
E10852
|
entity |
| Predicate | typeOfDivision |
P15261
|
FINISHED |
| Object | intermediate church structure |
—
|
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: intermediate church structure | Statement: [Province VI, typeOfDivision, intermediate church structure]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfDivision Context triple: [Province VI, typeOfDivision, intermediate church structure]
-
A.
division
Indicates a relationship where one entity is separated or partitioned into parts, groups, or sections based on some criterion or operation.
-
B.
dividedBy
Indicates that one quantity is separated into a specified number of equal parts or groups by another quantity, representing a division relationship between them.
-
C.
canonicalDivision
Indicates that one entity is the standard or officially recognized subdivision or partition of another entity.
-
D.
dividendType
Indicates the classification of a dividend based on its nature or form (e.g., cash, stock, special), specifying what kind of dividend is being distributed.
-
E.
divisionTitle
Indicates the formal name or title assigned to a specific division within a larger organization or structure.
- F. None of above. chosen
Provenance (4 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_69a2e84b16c4819088d284c47c3a7968 |
completed | Feb. 28, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69a2f1b4f01881908b408357ff113308 |
completed | Feb. 28, 2026, 1:46 p.m. |
| PD | Predicate disambiguation | batch_69a2f018129c81909494450fcba71b59 |
completed | Feb. 28, 2026, 1:39 p.m. |
| PDg | Predicate description generation | batch_69a2f0f73af88190bc8f00c2047cc8b8 |
completed | Feb. 28, 2026, 1:43 p.m. |
Created at: Feb. 28, 2026, 1:12 p.m.