Triple
T19869372
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Apasmara |
E477471
|
entity |
| Predicate | bodyPartTrampling |
P83730
|
FINISHED |
| Object | right foot of Shiva |
—
|
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: right foot of Shiva | Statement: [Apasmara, bodyPartTrampling, right foot of Shiva]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bodyPartTrampling Context triple: [Apasmara, bodyPartTrampling, right foot of Shiva]
-
A.
tramples
chosen
Indicates that one entity crushes, damages, or overrides another by forcefully stepping or pressing down on it, often implying dominance or disregard.
-
B.
usesGroundFor
Indicates that one entity makes functional or practical use of a particular ground, surface, or land area for its activities or purposes.
-
C.
hasFootstomps
Indicates that one entity performs or possesses foot-stomping actions or behaviors in relation to another entity or context.
-
D.
isClimbedBarefootBySomePilgrims
Indicates that some pilgrims climb the referenced entity without wearing any footwear.
-
E.
fallType
Indicates the specific kind or category of fall that occurred in a falling event.
- 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_69d8e51e7d948190aedbcd6c30361c39 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e658a2cc8481908d134b0b5cf79d06 |
completed | April 20, 2026, 4:47 p.m. |
| PD | Predicate disambiguation | batch_69e537e8c4e481909fe95d795b4864e7 |
completed | April 19, 2026, 8:15 p.m. |
Created at: April 10, 2026, 1:51 p.m.