Triple
T11438808
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sarangapani Temple |
E271081
|
entity |
| Predicate | numberOfPrakarams |
P75233
|
FINISHED |
| Object | two |
—
|
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: two | Statement: [Sarangapani Temple, numberOfPrakarams, two]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: numberOfPrakarams Context triple: [Sarangapani Temple, numberOfPrakarams, two]
-
A.
hasNumberOfPrakaras
chosen
Indicates the relationship specifying how many prakaras (enclosure layers or surrounding structures) are associated with a given entity.
-
B.
numberOfPadarthas
Indicates the relationship that specifies how many distinct padarthas (categories or entities) are associated with or contained in a given subject.
-
C.
numberOfGopurams
Indicates the specific count of gopurams (temple gateway towers) associated with an entity.
-
D.
numberOfOpenworkStupas
Indicates the count of openwork stupas associated with or present at a given subject.
-
E.
principlesCount
Indicates the number of principles associated with or applicable to a given entity or 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_69d6aadeef688190874bcecd88b3dd9b |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8088711ec8190afae9f4d9f2a11ca |
completed | April 9, 2026, 8:13 p.m. |
| PD | Predicate disambiguation | batch_69d7e7162b288190a0bfb89f7eb747c7 |
completed | April 9, 2026, 5:51 p.m. |
Created at: April 8, 2026, 9:35 p.m.