Triple
T3838199
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gorgonia |
E93386
|
entity |
| Predicate | hasMiracleAssociated |
P41944
|
FINISHED |
| Object | healing from severe injuries after a fall |
—
|
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: healing from severe injuries after a fall | Statement: [Gorgonia, hasMiracleAssociated, healing from severe injuries after a fall]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMiracleAssociated Context triple: [Gorgonia, hasMiracleAssociated, healing from severe injuries after a fall]
-
A.
miracleDescription
chosen
Indicates that a miraculous event or phenomenon is being described or characterized.
-
B.
miraclePerformedBy
Indicates that a miraculous event is carried out or caused by a particular agent or entity.
-
C.
numberOfMiraclesTraditionallyAssociated
Indicates the traditionally recognized count of miracles that are associated with a particular entity or subject.
-
D.
keyMiracle
Indicates that an event or action is regarded as a central or decisive miracle within a given context or narrative.
-
E.
hasMythicEvent
Indicates that an entity is associated with, involves, or features a significant mythic or legendary event.
- 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_69aed96ce578819084ab16e3439976c9 |
completed | March 9, 2026, 2:30 p.m. |
| NER | Named-entity recognition | batch_69aeeb9d11f081909fc51e84657ec7f1 |
completed | March 9, 2026, 3:47 p.m. |
| PD | Predicate disambiguation | batch_69aee74dcecc819098285483ec721b40 |
completed | March 9, 2026, 3:29 p.m. |
Created at: March 9, 2026, 3:18 p.m.