Triple
T25232429
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jumboo Savari |
E632249
|
entity |
| Predicate | carriesOnHowdah |
P126461
|
FINISHED |
| Object | idol of Goddess Chamundeshwari |
—
|
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: idol of Goddess Chamundeshwari | Statement: [Jumboo Savari, carriesOnHowdah, idol of Goddess Chamundeshwari]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: carriesOnHowdah Context triple: [Jumboo Savari, carriesOnHowdah, idol of Goddess Chamundeshwari]
-
A.
carriedBy
Indicates that one entity is physically supported and transported by another entity.
-
B.
carriageType
Indicates the specific kind or category of carriage associated with or used in relation to an entity.
-
C.
carriesOnBack
Indicates that one entity supports and transports another entity positioned on its back.
-
D.
carriedVehicleMount
chosen
Indicates that one entity serves as a vehicle-mounted platform used to transport or carry another entity.
-
E.
hasCarryingHandle
Indicates that one entity possesses a handle specifically designed to allow it to be carried.
- 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_69e75a8ec5f88190b9eba06ae42b413a |
completed | April 21, 2026, 11:07 a.m. |
| NER | Named-entity recognition | batch_69f47df5eafc819089a2735bd8177a27 |
completed | May 1, 2026, 10:18 a.m. |
| PD | Predicate disambiguation | batch_69f4683472ec8190a483b3b8afe71720 |
completed | May 1, 2026, 8:45 a.m. |
Created at: April 21, 2026, 1:06 p.m.