Triple
T30746192
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kalimat-i-Firdawsíyyih |
E782821
|
entity |
| Predicate | religiousCorpus |
P34765
|
FINISHED |
| Object | Writings of Bahá’u’lláh |
—
|
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: Writings of Bahá’u’lláh | Statement: [Kalimat-i-Firdawsíyyih, religiousCorpus, Writings of Bahá’u’lláh]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: religiousCorpus Context triple: [Kalimat-i-Firdawsíyyih, religiousCorpus, Writings of Bahá’u’lláh]
-
A.
religiousTextType
Indicates that one entity is a religious text and specifies the type or category of that religious text in relation to the other entity.
-
B.
religiousTextOf
Indicates that one entity is a religious text that is sacred to, foundational for, or primarily associated with another entity (such as a religion, denomination, or faith community).
-
C.
religiousTextCategory
Indicates that a religious text belongs to or is classified under a particular category or type.
-
D.
religiousTextTradition
chosen
Indicates that a religious text is associated with, originates from, or is authoritative within a particular religious tradition or denomination.
-
E.
religiousTextMentionedIn
Indicates that a religious text is referenced, cited, or discussed within another work or source.
- 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_69f224af8d8481908bea03890c5618be |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69fe610e1f6881908f10070ba64643cf |
completed | May 8, 2026, 10:17 p.m. |
| PD | Predicate disambiguation | batch_69fe604c6c008190ad659e9b9fa82f7b |
completed | May 8, 2026, 10:14 p.m. |
Created at: April 29, 2026, 8:38 p.m.