Triple
T19484448
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nandikeshvara |
E487472
|
entity |
| Predicate | directionFacedInTemples |
P111924
|
FINISHED |
| Object | towards the main Shiva linga |
—
|
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: towards the main Shiva linga | Statement: [Nandikeshvara, directionFacedInTemples, towards the main Shiva linga]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: directionFacedInTemples Context triple: [Nandikeshvara, directionFacedInTemples, towards the main Shiva linga]
-
A.
mainShrineOrientation
chosen
Indicates the directional alignment or facing direction of a main shrine relative to a reference point or axis.
-
B.
positionInTemple
Indicates the specific location or role an entity occupies within a temple.
-
C.
templeType
Indicates the specific category or classification of a temple in terms of its form, function, or religious/architectural style.
-
D.
viewFromTemple
Indicates a spatial relationship where a particular view or scene is observed from the vantage point of a temple.
-
E.
sacredDirection
Indicates a directional relationship that is regarded as holy, spiritually significant, or ritually privileged within a religious or cultural context.
- 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_69d8e8d924388190b847cb15bb3d0aff |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e6343dcc748190b0df816e6ab4cafb |
completed | April 20, 2026, 2:12 p.m. |
| PD | Predicate disambiguation | batch_69e4fd7883308190b73912a71a35a835 |
completed | April 19, 2026, 4:06 p.m. |
Created at: April 10, 2026, 1:39 p.m.