Triple
T25657854
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Evil |
E643285
|
entity |
| Predicate | affiliatedOrganizationInStory |
P117061
|
FINISHED |
| Object | Catholic Church |
—
|
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: Catholic Church | Statement: [Evil, affiliatedOrganizationInStory, Catholic Church]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: affiliatedOrganizationInStory Context triple: [Evil, affiliatedOrganizationInStory, Catholic Church]
-
A.
parentOrganizationInStory
Indicates that one organization functions as the parent or overarching organization of another within the context of a specific story or narrative.
-
B.
networkAffiliationInStory
Indicates that, within the context of a story, an entity is affiliated with or belongs to a particular network (such as a media, broadcast, or organizational network).
-
C.
organizationInStory
Indicates that an organization appears or plays a role within the context of a specific story.
-
D.
connectedOrganization
chosen
Indicates that there is an established relationship or association between two organizations, such that one is linked or affiliated with the other in some relevant context.
-
E.
associatedOrganizationFullName
Indicates that an entity is linked to an organization by specifying the organization’s complete, official name.
- 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_69e77e7d8a848190a98d0162325fd780 |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f5faece90c8190826cd3bd3614c10d |
completed | May 2, 2026, 1:23 p.m. |
| PD | Predicate disambiguation | batch_69f4a0f7c6008190ae8cee3e71e19b94 |
completed | May 1, 2026, 12:47 p.m. |
Created at: April 21, 2026, 6:36 p.m.