Triple
T902536
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ramayana |
E19476
|
entity |
| Predicate | approximateVerses |
P7673
|
FINISHED |
| Object | about 24,000 shlokas |
—
|
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 24,000 shlokas | Statement: [Ramayana, approximateVerses, about 24,000 shlokas]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: approximateVerses Context triple: [Ramayana, approximateVerses, about 24,000 shlokas]
-
A.
approximateNumberOfVerses
chosen
Indicates an estimated or approximate count of verses associated with an entity.
-
B.
verses
Indicates a relationship where one entity competes or is pitted against another, as in an opposition, matchup, or comparison.
-
C.
hasVerseCount
Indicates that an entity (such as a text or section) is associated with a specific number of verses it contains.
-
D.
hasMultipleVerses
Indicates that something, typically a song, poem, or text, consists of more than one verse.
-
E.
keyVerse
Indicates that one verse is designated as the central or most thematically important verse in relation to a text, passage, or concept.
- 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_69a4939e889c8190ac148b3ac1a7f90b |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4ad56f4c08190a7a5091ff0eb3209 |
completed | March 1, 2026, 9:19 p.m. |
| PD | Predicate disambiguation | batch_69a4aa98caec8190bbcc38320090f058 |
completed | March 1, 2026, 9:07 p.m. |
Created at: March 1, 2026, 7:39 p.m.