Triple
T35358249
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Prabodhini Ekadashi |
E1021396
|
entity |
| Predicate | precedesFestival |
P109657
|
FINISHED |
| Object | Kartik Purnima |
—
|
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: Kartik Purnima | Statement: [Prabodhini Ekadashi, precedesFestival, Kartik Purnima]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: precedesFestival Context triple: [Prabodhini Ekadashi, precedesFestival, Kartik Purnima]
-
A.
determinesFestival
Indicates that one entity decides, defines, or selects which festival is applicable or will occur for another entity or context.
-
B.
festivalFunction
Indicates that an event serves as a festival or is functioning in the role of a festival within a given context.
-
C.
hasFestivalDepicted
Indicates that a work or representation includes a depiction or portrayal of a festival.
-
D.
feastPrecededBy
chosen
Indicates that one feast occurs after and is temporally preceded by another feast.
-
E.
festivalSystem
Indicates a relationship where an entity is part of, managed by, or associated with a festival-related organizational or operational system.
- 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_69f76def44c881908a20e8008572eb44 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69fd884cb2b48190b6acd473430d9e19 |
completed | May 8, 2026, 6:53 a.m. |
| PD | Predicate disambiguation | batch_69fd8709ca208190a8bab836f0156af5 |
completed | May 8, 2026, 6:47 a.m. |
Created at: May 3, 2026, 4:03 p.m.