Triple
T35011741
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Nine Divines |
E1009952
|
entity |
| Predicate | hasHolyText |
P1184
|
FINISHED |
| Object | Ten Commands of the Nine Divines |
—
|
NE NERFINISHED |
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: Ten Commands of the Nine Divines | Statement: [The Nine Divines, hasHolyText, Ten Commands of the Nine Divines]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasHolyText Context triple: [The Nine Divines, hasHolyText, Ten Commands of the Nine Divines]
-
A.
hasSacredText
chosen
Indicates that an entity possesses or is associated with a particular sacred or religious text.
-
B.
hasLiturgicalTexts
Indicates that an entity possesses or is associated with specific liturgical texts used in religious worship or ceremonies.
-
C.
hasPrimaryBiblicalText
Indicates that one entity is associated with another entity that serves as its main or authoritative biblical text.
-
D.
hasScripture
Indicates that one entity possesses, is associated with, or is defined by a particular scripture or set of scriptural texts.
-
E.
hasLiturgicalBook
Indicates that one entity possesses, uses, or is associated with a specific liturgical book in a religious or worship 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_69f76dcc3ac8819096a3ed52f5fa2523 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69fd974d75e08190af46b1d608769f3b |
completed | May 8, 2026, 7:57 a.m. |
| PD | Predicate disambiguation | batch_69fd94ff792c8190bedf4a639d3da809 |
completed | May 8, 2026, 7:47 a.m. |
Created at: May 3, 2026, 4:01 p.m.