Triple
T17939121
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hemanta |
E448541
|
entity |
| Predicate | festivalsOftenOccurringIn |
P29256
|
FINISHED |
| Object | Kartika Purnima period (by overlap) |
—
|
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: Kartika Purnima period (by overlap) | Statement: [Hemanta, festivalsOftenOccurringIn, Kartika Purnima period (by overlap)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: festivalsOftenOccurringIn Context triple: [Hemanta, festivalsOftenOccurringIn, Kartika Purnima period (by overlap)]
-
A.
festivalHeldIn
Indicates that a festival takes place or is hosted at a specific location or venue.
-
B.
shareCulturalFestivals
Indicates that two or more entities participate in or observe the same cultural festivals or celebrations.
-
C.
festivalObserved
Indicates that a particular festival is celebrated, observed, or commemorated by an entity (such as a person, group, or community).
-
D.
festivalSeason
chosen
Indicates that a time period is designated or recognized as the season during which a particular festival or set of festivals takes place.
-
E.
festivalActivity
Indicates that an entity is an event, performance, or engagement that takes place as part of a festival’s organized program.
- 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_69d8b9f79d14819095540856928f0e25 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4ad9455fc81908bf595f9ed42c624 |
completed | April 19, 2026, 10:25 a.m. |
| PD | Predicate disambiguation | batch_69e3f8e713d481908b4a126258c18b63 |
completed | April 18, 2026, 9:34 p.m. |
Created at: April 10, 2026, 10:21 a.m.