Triple
T22529583
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kaumodaki |
E556997
|
entity |
| Predicate | heldInHand |
P87059
|
FINISHED |
| Object | Vishnu’s lower left hand in many depictions |
—
|
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: Vishnu’s lower left hand in many depictions | Statement: [Kaumodaki, heldInHand, Vishnu’s lower left hand in many depictions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: heldInHand Context triple: [Kaumodaki, heldInHand, Vishnu’s lower left hand in many depictions]
-
A.
depictedHolding
Indicates that one entity is shown in an image or representation as physically holding or grasping another entity.
-
B.
heldAround
Indicates that one entity is held in a way that surrounds or encircles another entity.
-
C.
canBeHeldWith
Indicates that two entities are compatible or suitable to be held or used together at the same time.
-
D.
carriedInRightOrLeftHand
chosen
Indicates that an entity is being held and transported either in the right hand or in the left hand of an agent.
-
E.
heldAs
Indicates that one entity is kept, maintained, or regarded in a particular state, role, or condition by another entity.
- 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_69e11e57483c8190b0887c4f8ff26446 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15ed5b5d081909d927f8aee44b673 |
completed | April 29, 2026, 1:28 a.m. |
| PD | Predicate disambiguation | batch_69e898c864148190a3f5feec7967d49c |
completed | April 22, 2026, 9:45 a.m. |
Created at: April 16, 2026, 8:51 p.m.