Triple
T37894187
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | American Lutheran Church |
E945228
|
entity |
| Predicate | approximateMembershipAtMerger |
P201229
|
FINISHED |
| Object | about 2.25 million members |
—
|
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: about 2.25 million members | Statement: [American Lutheran Church, approximateMembershipAtMerger, about 2.25 million members]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: approximateMembershipAtMerger Context triple: [American Lutheran Church, approximateMembershipAtMerger, about 2.25 million members]
-
A.
someMembersMergedWith
Indicates that a subset of members from one group combined or integrated with members of another group to form a unified entity or subgroup.
-
B.
laterMergedWith
Indicates that one entity was combined into and became part of another entity at a subsequent point in time.
-
C.
participatedInMergerContext
Indicates that an entity took part in a specific merger event or merger-related context.
-
D.
mergerPeriod
Indicates the time span during which two or more entities are in the process of merging into a single combined entity.
-
E.
losesMembershipWhen
Indicates that an entity ceases to be a member of another entity or group when a specified condition or event occurs.
- 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_69f76ef0e8708190987c7254ed8c7abe |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69ffdf47d9608190830ca23d9cef6409 |
completed | May 10, 2026, 1:28 a.m. |
| PD | Predicate disambiguation | batch_69ffdf00e2b4819082dd5cb78f316baf |
completed | May 10, 2026, 1:27 a.m. |
| PDg | Predicate description generation | batch_69ffdf46e18c8190a5e4f4e5211cb087 |
completed | May 10, 2026, 1:28 a.m. |
Created at: May 3, 2026, 4:19 p.m.