Triple
T8614739
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vandiyur Mariamman Teppakulam |
E204006
|
entity |
| Predicate | floatFestivalFeature |
P44899
|
FINISHED |
| Object | decorated floats |
—
|
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: decorated floats | Statement: [Vandiyur Mariamman Teppakulam, floatFestivalFeature, decorated floats]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: floatFestivalFeature Context triple: [Vandiyur Mariamman Teppakulam, floatFestivalFeature, decorated floats]
-
A.
festivalAttracts
Indicates that a festival draws or brings in attendees, participants, or interest toward itself.
-
B.
exampleFestival
Indicates that an entity is an instance or example of a particular festival event or type of festival.
-
C.
festivalFocus
chosen
Indicates that a festival is centered around, dedicated to, or thematically focused on a particular subject, activity, or feature.
-
D.
festivalActivity
Indicates that an entity is an event, performance, or engagement that takes place as part of a festival’s organized program.
-
E.
featuresEvent
Indicates that an entity includes, presents, or highlights a particular event as part of its content or offering.
- 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_69ca832ceab8819096e4a9f546695079 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cc47020748819090f658c115c1a7b9 |
completed | March 31, 2026, 10:13 p.m. |
| PD | Predicate disambiguation | batch_69cc455437488190b7506f820daf6e32 |
completed | March 31, 2026, 10:06 p.m. |
Created at: March 30, 2026, 6:25 p.m.