Triple
T11103101
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Prayer to Saint Michael |
E262559
|
entity |
| Predicate | invokesRoleOfMichael |
P97296
|
FINISHED |
| Object | defender of the Church |
—
|
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: defender of the Church | Statement: [Prayer to Saint Michael, invokesRoleOfMichael, defender of the Church]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: invokesRoleOfMichael Context triple: [Prayer to Saint Michael, invokesRoleOfMichael, defender of the Church]
-
A.
playRoleIn
Indicates that an entity participates in or performs a specific function, character, or part within an event, context, or system.
-
B.
speakerRole
Indicates the functional role or capacity in which an entity is acting as a speaker within a communicative event.
-
C.
playsInRole
Indicates that an entity performs or appears in a specific role within a production, event, or context.
-
D.
roleInDialogue
Indicates that an entity participates in a dialogue with a specific conversational role (e.g., speaker, listener, moderator) relative to other participants.
-
E.
roleInGemini3
Indicates that an entity holds a specific role or function within the Gemini 3 mission or project.
- F. None of above. chosen
Provenance (4 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_69d6aa9a40d88190a373e2c7e48285db |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d79a2c30a481908c45020c37caebe4 |
completed | April 9, 2026, 12:23 p.m. |
| PD | Predicate disambiguation | batch_69d7441aa3548190b92dbde57841c135 |
completed | April 9, 2026, 6:15 a.m. |
| PDg | Predicate description generation | batch_69d750ca52ec8190a559432a5de106fd |
completed | April 9, 2026, 7:10 a.m. |
Created at: April 8, 2026, 9:27 p.m.