Triple
T18556002
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ganesha Ratha |
E453503
|
entity |
| Predicate | sanctumContains |
P132141
|
FINISHED |
| Object | image of Ganesha |
—
|
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: image of Ganesha | Statement: [Ganesha Ratha, sanctumContains, image of Ganesha]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sanctumContains Context triple: [Ganesha Ratha, sanctumContains, image of Ganesha]
-
A.
hasMainSanctum
Indicates that an entity possesses a primary or central sacred space used for core religious or spiritual activities.
-
B.
otherRelatedSanctums
Indicates that there exist additional sanctums that are related or connected to a given sanctum in some relevant way.
-
C.
hasSanctuary
Indicates that one entity provides or serves as a place of refuge, protection, or safe haven for another entity.
-
D.
oneOfMultipleSanctums
Indicates that an entity is one among several sanctums associated with or available to another entity.
-
E.
isInSanctuaryWith
Indicates that two or more entities are located together within the same sanctuary or protected refuge at the same time.
- F. None of above. chosen
Provenance (4 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_69d8d388b0c881908e610a1c45b52640 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e53806046481908efbbe6909b2c68b |
completed | April 19, 2026, 8:16 p.m. |
| PD | Predicate disambiguation | batch_69e469e274a48190a570b25cfef4d890 |
completed | April 19, 2026, 5:36 a.m. |
| PDg | Predicate description generation | batch_69e46d2b93bc8190a6070018d7046547 |
completed | April 19, 2026, 5:50 a.m. |
Created at: April 10, 2026, 11:38 a.m.