Triple
T5050850
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bhagavata Purana |
E113780
|
entity |
| Predicate | traditionalNumberOfVerses |
P8730
|
FINISHED |
| Object | 18000 |
—
|
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: 18000 | Statement: [Bhagavata Purana, traditionalNumberOfVerses, 18000]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: traditionalNumberOfVerses Context triple: [Bhagavata Purana, traditionalNumberOfVerses, 18000]
-
A.
approximateNumberOfVerses
Indicates an estimated or approximate count of verses associated with an entity.
-
B.
hasVerseCount
chosen
Indicates that an entity (such as a text or section) is associated with a specific number of verses it contains.
-
C.
mostVersesChapter
Indicates that a chapter has the highest number of verses compared to all other chapters within the same collection or text.
-
D.
containsVerse
Indicates that one entity (typically a text or collection) includes a specific verse as part of its content.
-
E.
verseNumber
Indicates the specific numbered position of a verse within an ordered sequence, such as in a chapter, song, or poem.
- 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_69bd443aa1f88190abb992d138f2cf42 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd7425df74819091cfde348dd16a68 |
completed | March 20, 2026, 4:21 p.m. |
| PD | Predicate disambiguation | batch_69bd715479f08190933604aebd34414f |
completed | March 20, 2026, 4:09 p.m. |
Created at: March 20, 2026, 1:37 p.m.