Triple
T27646522
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nandi mandapa |
E696726
|
entity |
| Predicate | locationWithinComplex |
P143279
|
FINISHED |
| Object | in front of the main shrine |
—
|
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: in front of the main shrine | Statement: [Nandi mandapa, locationWithinComplex, in front of the main shrine]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locationWithinComplex Context triple: [Nandi mandapa, locationWithinComplex, in front of the main shrine]
-
A.
positionWithinComplex
Indicates that one entity is located inside or forms a component part of a larger complex or compound structure.
-
B.
coordinatesWithin
Indicates that one set of coordinates lies entirely inside the spatial bounds defined by another.
-
C.
locationInArchitecture
chosen
Indicates the spatial position or placement of one architectural element or feature within or relative to another architectural structure or context.
-
D.
housedWithinComplex
Indicates that one entity is located inside and functionally part of a larger building or facility complex.
-
E.
locatedWith
Indicates that two or more entities are situated together in the same place or spatial 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_69ef590abd3c8190834d0193bde12007 |
completed | April 27, 2026, 12:39 p.m. |
| NER | Named-entity recognition | batch_69ff109695008190a22b47ef8be2e3f9 |
completed | May 9, 2026, 10:46 a.m. |
| PD | Predicate disambiguation | batch_69ff0f243ea88190970d2c520b55c816 |
completed | May 9, 2026, 10:40 a.m. |
Created at: April 27, 2026, 2:29 p.m.