Triple
T27079698
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Uma |
E685557
|
entity |
| Predicate | hasFestivalDepicted |
P167115
|
FINISHED |
| Object | Durga Puja |
—
|
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: Durga Puja | Statement: [Uma, hasFestivalDepicted, Durga Puja]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFestivalDepicted Context triple: [Uma, hasFestivalDepicted, Durga Puja]
-
A.
hasFestival
Indicates that a location, community, or entity hosts or holds a festival or celebratory event.
-
B.
hasFestivalAttraction
Indicates that a festival includes or features a particular attraction as part of its offerings.
-
C.
hasFestivalContext
Indicates that something is related to, occurs within, or is characterized by the setting, activities, or circumstances of a festival.
-
D.
hasFestivalSection
Indicates that something includes or is associated with a specific section or category within a festival.
-
E.
hasFestivalConnection
Indicates a relationship in which two entities are connected through a festival, such as by participation, organization, sponsorship, or association with that event.
- F. None of above. chosen
Provenance (4 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_69ef14843b1481909d828b3d5a44550a |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69f6653ccf648190b65fb1141928e47e |
completed | May 2, 2026, 8:57 p.m. |
| PD | Predicate disambiguation | batch_69f6633451948190bcc0410602bb4914 |
completed | May 2, 2026, 8:48 p.m. |
| PDg | Predicate description generation | batch_69f663ff176c8190aaadb475f75daee4 |
completed | May 2, 2026, 8:52 p.m. |
Created at: April 27, 2026, 8:33 a.m.