Triple
T28808608
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | bēl mīšari |
E727446
|
entity |
| Predicate | deityFunctionHighlighted |
P118407
|
FINISHED |
| Object | judge of gods and humans |
—
|
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: judge of gods and humans | Statement: [bēl mīšari, deityFunctionHighlighted, judge of gods and humans]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: deityFunctionHighlighted Context triple: [bēl mīšari, deityFunctionHighlighted, judge of gods and humans]
-
A.
refersToDeityFunction
chosen
Indicates that one entity denotes, describes, or points to the role, power, or functional aspect of a deity.
-
B.
mainDeity
Indicates that one entity serves as the primary or chief deity worshiped, revered, or associated with another entity (such as a religion, temple, or culture).
-
C.
depictedDeity
Indicates that one entity is a deity who is shown or represented in an image, artwork, or visual depiction associated with another entity.
-
D.
targetedDeity
Indicates that an action, event, or entity is specifically directed toward or aimed at a particular deity.
-
E.
portraysDeity
Indicates that one entity represents, depicts, or characterizes another entity as a deity or divine being.
- 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_69f0319c38948190bca746ad60fd25ba |
completed | April 28, 2026, 4:03 a.m. |
| NER | Named-entity recognition | batch_69f658ee40088190b71e1219407690d0 |
completed | May 2, 2026, 8:05 p.m. |
| PD | Predicate disambiguation | batch_69f65760fd3081908ffe014a5e2bf069 |
completed | May 2, 2026, 7:58 p.m. |
Created at: April 28, 2026, 6:30 a.m.