Triple
T2362931
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Unction of the Sick |
E47314
|
entity |
| Predicate | reformedName |
P33642
|
FINISHED |
| Object | Anointing of the Sick after Second Vatican Council |
—
|
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: Anointing of the Sick after Second Vatican Council | Statement: [Unction of the Sick, reformedName, Anointing of the Sick after Second Vatican Council]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reformedName Context triple: [Unction of the Sick, reformedName, Anointing of the Sick after Second Vatican Council]
-
A.
reformName
chosen
Indicates that an entity has undergone a reform or change resulting in a new name or designation.
-
B.
reformedOffice
Indicates that an office or official position has been reorganized, restructured, or fundamentally changed from its previous form.
-
C.
formerName
Indicates that an entity was previously known by a different name in the past.
-
D.
nameRestored
Indicates that an entity’s original or correct name has been reinstated after having been changed, lost, or altered.
-
E.
reformedBody
Indicates that an entity has undergone a process of structural or organizational change resulting in a newly formed or reorganized body.
- 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_69a88a1a4a6081908645b0f2914521ab |
completed | March 4, 2026, 7:38 p.m. |
| NER | Named-entity recognition | batch_69abc74501388190adce9b3e51a03ded |
completed | March 7, 2026, 6:35 a.m. |
| PD | Predicate disambiguation | batch_69abc599b92c819093d9e15d4437705d |
completed | March 7, 2026, 6:28 a.m. |
Created at: March 4, 2026, 7:55 p.m.