Triple
T33849950
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Holy Cross Cathedral, Honiara |
E867593
|
entity |
| Predicate | hasDenominationMajority |
P19261
|
FINISHED |
| Object | Roman Catholic |
—
|
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: Roman Catholic | Statement: [Holy Cross Cathedral, Honiara, hasDenominationMajority, Roman Catholic]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDenominationMajority Context triple: [Holy Cross Cathedral, Honiara, hasDenominationMajority, Roman Catholic]
-
A.
hasMajority
Indicates that one entity holds more than half of the total share, control, or quantity in relation to another entity or set.
-
B.
hasMajorityOf
Indicates that one entity possesses or controls more than half of the total quantity, members, or share of another entity.
-
C.
hasMajorityIn
Indicates that one entity holds more than half of the control, ownership, or representation within another entity or group.
-
D.
majorityDenomination
chosen
Indicates that a specified religious denomination constitutes the largest share of a given population or group.
-
E.
heldByMajority
Indicates that something (such as a position, opinion, or ownership) is possessed or supported by more than half of the relevant group or participants.
- 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_69f349937b648190a34ada70f6a2b534 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69fefa064ab48190925759950d0d94d9 |
completed | May 9, 2026, 9:10 a.m. |
| PD | Predicate disambiguation | batch_69fef96ae5d08190b027435753c44821 |
completed | May 9, 2026, 9:07 a.m. |
Created at: May 1, 2026, 1:47 a.m.