Triple
T11109188
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eparchy of Lugoj |
E262709
|
entity |
| Predicate | typeOfFaithfulServed |
P37691
|
FINISHED |
| Object | Romanian Greek Catholic faithful |
—
|
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: Romanian Greek Catholic faithful | Statement: [Eparchy of Lugoj, typeOfFaithfulServed, Romanian Greek Catholic faithful]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfFaithfulServed Context triple: [Eparchy of Lugoj, typeOfFaithfulServed, Romanian Greek Catholic faithful]
-
A.
servesFaithfulOf
chosen
Indicates that one entity performs services or acts in a ministering or supportive role for those who are faithful to another entity.
-
B.
isTypicallyServedFor
Indicates that one item is most commonly or customarily served as a meal or course for the other (e.g., a dish typically served for breakfast, lunch, or dinner).
-
C.
typeOfAssemblyServed
Indicates the specific type or category of assembly that is being served or catered to by an entity or action.
-
D.
servesType
Indicates that one entity provides, offers, or is used to deliver a particular type, category, or kind of thing or service.
-
E.
servingStyle
Indicates how something (typically food or drink) is presented or offered for consumption or use.
- 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_69d6aa9b46cc8190b19f9f0cc45bf322 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d79a6896c0819082685b5b4600d158 |
completed | April 9, 2026, 12:24 p.m. |
| PD | Predicate disambiguation | batch_69d7441cf8188190b8095f622c923156 |
completed | April 9, 2026, 6:15 a.m. |
Created at: April 8, 2026, 9:27 p.m.