Triple
T5686895
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brahma temple (Prambanan) |
E125334
|
entity |
| Predicate | hasSanctumImage |
P65787
|
FINISHED |
| Object | image of Brahma |
—
|
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 Brahma | Statement: [Brahma temple (Prambanan), hasSanctumImage, image of Brahma]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSanctumImage Context triple: [Brahma temple (Prambanan), hasSanctumImage, image of Brahma]
-
A.
hasKeyImage
Indicates that one entity is designated as the primary or representative image associated with another entity.
-
B.
hasSanctuary
Indicates that one entity provides or serves as a place of refuge, protection, or safe haven for another entity.
-
C.
hasHiddenImage
Indicates that an entity contains or is associated with an image that is not immediately visible or is intentionally concealed from normal view.
-
D.
hasImageType
Indicates that an entity is associated with an image of a particular type or format.
-
E.
hasMainImageSource
Indicates that an entity is associated with a primary image file or URL that serves as its main visual representation.
- 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_69c0082a884c8190a79001bae658941f |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c0248751bc8190b12aaa42d1ef17e3 |
completed | March 22, 2026, 5:19 p.m. |
| PD | Predicate disambiguation | batch_69c021be59088190a81c880957f666ab |
completed | March 22, 2026, 5:07 p.m. |
| PDg | Predicate description generation | batch_69c024861bc88190a17782c1982fbb3e |
completed | March 22, 2026, 5:19 p.m. |
Created at: March 22, 2026, 3:44 p.m.