Triple
T37514097
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zakarum faith |
E932588
|
entity |
| Predicate | scriptureTheme |
P13857
|
FINISHED |
| Object | Light as absolute truth |
—
|
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: Light as absolute truth | Statement: [Zakarum faith, scriptureTheme, Light as absolute truth]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: scriptureTheme Context triple: [Zakarum faith, scriptureTheme, Light as absolute truth]
-
A.
scripturalTheme
chosen
Indicates that one entity represents a central religious or theological theme expressed, discussed, or emphasized within a scriptural text or passage.
-
B.
scriptureFocus
Indicates that something centers on, emphasizes, or is primarily concerned with religious scripture or sacred texts.
-
C.
scriptureFor
Indicates that one entity serves as a scriptural or authoritative religious text for another entity (such as a person, group, or belief system).
-
D.
scriptureType
Indicates the classification or category of a scripture in relation to its type or genre.
-
E.
scriptureAllusion
Indicates that one entity makes reference to, echoes, or is inspired by a passage, theme, or element from a scriptural text found in 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_69f76ec730988190b5aa4f9cb9afd518 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fd44474ed48190ac372e4c88d762ed |
completed | May 8, 2026, 2:02 a.m. |
| PD | Predicate disambiguation | batch_69fd41ef28a48190a66959be5c964461 |
completed | May 8, 2026, 1:52 a.m. |
Created at: May 3, 2026, 4:17 p.m.