Triple
T12250200
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marist Family |
E291950
|
entity |
| Predicate | religiousCharism |
P57647
|
FINISHED |
| Object | Marist charism |
—
|
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: Marist charism | Statement: [Marist Family, religiousCharism, Marist charism]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: religiousCharism Context triple: [Marist Family, religiousCharism, Marist charism]
-
A.
sharesCharismWith
Indicates that two entities possess and express the same or very similar spiritual gift, mission, or distinctive inspirational quality.
-
B.
religiousElement
Indicates that something is a component, aspect, or feature associated with a religion or religious practice.
-
C.
religiousCharacteristic
Indicates that one entity has a religious attribute, quality, or affiliation that characterizes or distinguishes it in a religious context.
-
D.
foundingCharism
chosen
Indicates the distinctive spiritual focus, mission, or guiding gift that characterizes the founding identity of a religious community or organization.
-
E.
religiousSceneSpecialization
Indicates a relationship where a scene is specifically characterized or classified by a particular religious theme, context, or function.
- 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_69d6ab67950c8190be08450a06228c4b |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d91d38ee10819093ed41d2954bf4ef |
completed | April 10, 2026, 3:54 p.m. |
| PD | Predicate disambiguation | batch_69d91c46dcd88190a263db30804bff36 |
completed | April 10, 2026, 3:50 p.m. |
Created at: April 8, 2026, 9:52 p.m.