Triple
T32048057
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kaminarimon |
E818404
|
entity |
| Predicate | hasProtectionSymbolism |
P34702
|
FINISHED |
| Object | warding off evil |
—
|
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: warding off evil | Statement: [Kaminarimon, hasProtectionSymbolism, warding off evil]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasProtectionSymbolism Context triple: [Kaminarimon, hasProtectionSymbolism, warding off evil]
-
A.
hasSacredSymbol
Indicates that one entity serves as a sacred or religiously significant symbol associated with another entity.
-
B.
emblemSymbolism
chosen
Indicates that one entity serves as an emblem whose design or features symbolically represent or convey meanings about another entity.
-
C.
hasProtectionPurpose
Indicates that something is intended or designed to serve a protective function or goal.
-
D.
believedToProtect
Indicates that one entity is thought or assumed to provide protection or defense for another entity.
-
E.
protectiveEmblemName
Indicates that a given name is the designated title or label of a protective emblem associated with an entity or context.
- 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_69f348fcfb648190859f6be5e04b7cfe |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_6a00a602b6b48190a9dea8ae22d2fa05 |
completed | May 10, 2026, 3:36 p.m. |
| PD | Predicate disambiguation | batch_6a00a559bf3881909a7b50776d8f47bb |
completed | May 10, 2026, 3:33 p.m. |
Created at: May 1, 2026, 12:20 a.m.