Triple
T36706248
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | tribunals of the Roman Curia |
E906366
|
entity |
| Predicate | highestAppealFrom |
P35238
|
FINISHED |
| Object | diocesan tribunals |
—
|
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: diocesan tribunals | Statement: [tribunals of the Roman Curia, highestAppealFrom, diocesan tribunals]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: highestAppealFrom Context triple: [tribunals of the Roman Curia, highestAppealFrom, diocesan tribunals]
-
A.
levelOfAppeal
Indicates the degree or intensity to which something is attractive, interesting, or desirable to someone or something.
-
B.
hasHighest
Indicates that one entity possesses the greatest value, rank, or level in a specified attribute or set compared to all others.
-
C.
ultimateAppealLiesTo
chosen
Indicates that the final level of appeal or review authority for a decision or case rests with a specified entity or body.
-
D.
highestOrgan
Indicates that one entity is the organ with the highest rank, level, or position within a specified system or hierarchy relative to another entity.
-
E.
appealsFor
Indicates that one entity formally requests support, intervention, or a favorable decision from another entity.
- 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_69f76e7195c48190b5580c9cfb01e95f |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fd8ccbd4c88190b13aae0673b3c821 |
completed | May 8, 2026, 7:12 a.m. |
| PD | Predicate disambiguation | batch_69fd8ae2227c819089546f5c3629799e |
completed | May 8, 2026, 7:04 a.m. |
Created at: May 3, 2026, 4:12 p.m.