Triple
T36826291
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Blessing of the Throats |
E910019
|
entity |
| Predicate | invokesIntercessionOf |
P62418
|
FINISHED |
| Object | Saint Blaise |
—
|
NE NERFINISHED |
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: Saint Blaise | Statement: [Blessing of the Throats, invokesIntercessionOf, Saint Blaise]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: invokesIntercessionOf Context triple: [Blessing of the Throats, invokesIntercessionOf, Saint Blaise]
-
A.
intercessorFor
Indicates that one entity acts as a mediator or advocate on behalf of another entity, typically intervening or pleading for them with a third party.
-
B.
viewOnIntercession
Indicates a stance or belief regarding the legitimacy, role, or effectiveness of intercession (such as mediating or praying on behalf of others).
-
C.
divineInteraction
Indicates an interaction or exchange occurring between a divine being (or force) and another entity.
-
D.
invocationWord
Indicates that a specific word or phrase is used to call upon, activate, or summon an entity, power, or process.
-
E.
invokesPower
chosen
Indicates that one entity calls upon, activates, or makes use of the power, authority, or special ability associated with 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_69f76e7e9d60819092442fba73290a46 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f7ca9c9ef88190b71bcc6f5b4a6182 |
completed | May 3, 2026, 10:22 p.m. |
| PD | Predicate disambiguation | batch_69f7c89b528c8190bf80b230fc7c7108 |
completed | May 3, 2026, 10:13 p.m. |
Created at: May 3, 2026, 4:13 p.m.