Triple
T2200219
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eye of Providence |
E50470
|
entity |
| Predicate | isOftenEnclosedIn |
P3100
|
FINISHED |
| Object | triangle |
—
|
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: triangle | Statement: [Eye of Providence, isOftenEnclosedIn, triangle]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isOftenEnclosedIn Context triple: [Eye of Providence, isOftenEnclosedIn, triangle]
-
A.
hasEnclosures
Indicates that an entity possesses or contains one or more enclosing structures, spaces, or bounded areas associated with it.
-
B.
oftenAccompaniedBy
chosen
Indicates that one entity is frequently found together with, occurs alongside, or is commonly associated in presence or use with another entity.
-
C.
ashesOftenShapedAs
Indicates that the remains of something, typically after burning, are frequently formed or molded into a particular shape or object.
-
D.
isFrequently
Indicates that an action, state, or relationship occurs often or with high regularity between the related entities.
-
E.
containsMostOf
Indicates that one entity includes the majority (but not necessarily all) of the substance, elements, or components of 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_69a88b044ab48190add007487680f009 |
completed | March 4, 2026, 7:41 p.m. |
| NER | Named-entity recognition | batch_69abbfa06bb4819092d7021358846e5f |
completed | March 7, 2026, 6:03 a.m. |
| PD | Predicate disambiguation | batch_69abbda706f4819094de73e1d1d1f539 |
completed | March 7, 2026, 5:54 a.m. |
Created at: March 4, 2026, 7:46 p.m.