Triple
T20133544
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kanchipuram silk saree |
E490959
|
entity |
| Predicate | hasPalluDecoration |
P23430
|
FINISHED |
| Object | heavy zari work |
—
|
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: heavy zari work | Statement: [Kanchipuram silk saree, hasPalluDecoration, heavy zari work]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPalluDecoration Context triple: [Kanchipuram silk saree, hasPalluDecoration, heavy zari work]
-
A.
hasTraditionalAttire
Indicates that an entity possesses or is associated with clothing that is customary or traditional within a particular culture or community.
-
B.
hasGhat
Indicates that a place or location possesses or is associated with a ghat (a series of steps or landing area leading to a body of water).
-
C.
hasDomeDecoration
Indicates that an entity’s dome is adorned with specific decorative elements or ornamentation.
-
D.
adornedWith
chosen
Indicates that one entity is decorated, embellished, or ornamented by another entity.
-
E.
hasFrill
Indicates that one entity possesses or is characterized by a frill as a distinguishing feature or component.
- 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_69da62651a0c8190a3e05e95e056a66b |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e66763ee908190af64af31b4ca2377 |
completed | April 20, 2026, 5:50 p.m. |
| PD | Predicate disambiguation | batch_69e54cfb0d0081908e789b9b57e96668 |
completed | April 19, 2026, 9:45 p.m. |
Created at: April 11, 2026, 11:32 p.m.