Triple
T6969009
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thrissur Pooram |
E161555
|
entity |
| Predicate | hasFireworksDisplay |
P45831
|
FINISHED |
| Object | early morning fireworks |
—
|
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: early morning fireworks | Statement: [Thrissur Pooram, hasFireworksDisplay, early morning fireworks]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFireworksDisplay Context triple: [Thrissur Pooram, hasFireworksDisplay, early morning fireworks]
-
A.
hasPyrotechnics
chosen
Indicates that an entity includes, uses, or features pyrotechnic effects or fireworks as part of its characteristics or activities.
-
B.
hasParades
Indicates that an entity regularly holds or hosts parades as events or activities.
-
C.
hasLightShow
Indicates that an entity features or presents a light-based visual display or performance.
-
D.
hasLaserShow
Indicates that an entity features or offers a laser-based visual show as part of its activities or attractions.
-
E.
hasParadeFeature
Indicates that an entity includes, exhibits, or is characterized by a particular feature or element of a parade.
- 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_69c68853cff881908439d488924a8283 |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6db152b2081909271493a5d1469fb |
completed | March 27, 2026, 7:31 p.m. |
| PD | Predicate disambiguation | batch_69c6d7c262508190a7708b3d9cf23d7c |
completed | March 27, 2026, 7:17 p.m. |
Created at: March 27, 2026, 2:30 p.m.