Triple
T20129868
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yaksha Prashna |
E490859
|
entity |
| Predicate | questionCountApproximate |
P15109
|
FINISHED |
| Object | over one hundred questions |
—
|
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: over one hundred questions | Statement: [Yaksha Prashna, questionCountApproximate, over one hundred questions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: questionCountApproximate Context triple: [Yaksha Prashna, questionCountApproximate, over one hundred questions]
-
A.
numberOfQuestions
chosen
Indicates the total count of questions associated with or contained in a given entity or context.
-
B.
sectionCountApproximate
Indicates that the number of sections associated with an entity is known only approximately rather than as an exact count.
-
C.
articleCountApprox
Indicates that the relationship specifies an approximate number of articles associated with an entity.
-
D.
subjectCount
Indicates the number of subjects associated with or involved in a given entity or context.
-
E.
questionsPerPassage
Indicates the number of questions that are associated with or derived from a single passage.
- 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_69da62651a0c8190a3e05e95e056a66b |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e66760b8f08190a66fbb2e9e3925a3 |
completed | April 20, 2026, 5:50 p.m. |
| PD | Predicate disambiguation | batch_69e54cfb0d0081908e789b9b57e96668 |
completed | April 19, 2026, 9:45 p.m. |
Created at: April 11, 2026, 11:31 p.m.