Triple
T4836222
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Virata Parva |
E108064
|
entity |
| Predicate | numberOfChaptersTraditional |
P2946
|
FINISHED |
| Object | about 4 sub-parvas |
—
|
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: about 4 sub-parvas | Statement: [Virata Parva, numberOfChaptersTraditional, about 4 sub-parvas]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: numberOfChaptersTraditional Context triple: [Virata Parva, numberOfChaptersTraditional, about 4 sub-parvas]
-
A.
numberOfChapters
chosen
Indicates the total count of chapters associated with a given entity.
-
B.
containsChapter
Indicates that one entity (typically a larger work or document) includes another entity as a chapter within its structure.
-
C.
numberOfPassages
Indicates the total count of distinct passages associated with or contained within a given entity or context.
-
D.
chapterNumber
Indicates the specific ordinal position a chapter occupies within a larger ordered work, such as a book or document.
-
E.
primarySourceChapters
Indicates that specific chapters are identified as the primary source material for the referenced content or work.
- 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_69bd43fbe444819085cb970706ef73f7 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6ff981fc819080d4466c6fe06cf3 |
completed | March 20, 2026, 4:04 p.m. |
| PD | Predicate disambiguation | batch_69bd6c21c7f08190846049d31fdfa144 |
completed | March 20, 2026, 3:47 p.m. |
Created at: March 20, 2026, 1:25 p.m.