Triple
T24115490
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | St Vincent’s Roman Catholic Church, Norden |
E597499
|
entity |
| Predicate | regularActivities |
P1164
|
FINISHED |
| Object | worship services |
—
|
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: worship services | Statement: [St Vincent’s Roman Catholic Church, Norden, regularActivities, worship services]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: regularActivities Context triple: [St Vincent’s Roman Catholic Church, Norden, regularActivities, worship services]
-
A.
typicalActivity
chosen
Indicates that an entity is commonly or characteristically engaged in a particular activity.
-
B.
activityType
Indicates the specific kind or category of action or event that an entity is engaged in or associated with.
-
C.
cycleOfActivity
Indicates a recurring sequence of actions or states that repeat over time as part of a process or behavior.
-
D.
activityTime
Indicates the time period during which an activity occurs or is scheduled to take place.
-
E.
earnActivity
Indicates that an entity gains or receives something of value (such as money, points, or rewards) as a result of performing a particular activity.
- 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_69e288c74200819098ab875b592cb39f |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1dedebb748190b8fe295d6dc0a9a7 |
completed | April 29, 2026, 10:35 a.m. |
| PD | Predicate disambiguation | batch_69f17651458c8190bbfd301883e46085 |
completed | April 29, 2026, 3:09 a.m. |
Created at: April 17, 2026, 11:04 p.m.