Triple
T23844885
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pokhran Test Range |
E591091
|
entity |
| Predicate | firstNuclearTestName |
P1207
|
FINISHED |
| Object | Smiling Buddha |
—
|
NE NERFINISHED |
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: Smiling Buddha | Statement: [Pokhran Test Range, firstNuclearTestName, Smiling Buddha]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstNuclearTestName Context triple: [Pokhran Test Range, firstNuclearTestName, Smiling Buddha]
-
A.
firstNuclearTest
chosen
Indicates the event in which an entity conducts its first-ever test of a nuclear explosive device.
-
B.
firstThermonuclearTest
Indicates that the subject entity conducted or was responsible for the first thermonuclear (hydrogen bomb) test associated with the object entity.
-
C.
firstNuclearTestDate
Indicates the date on which an entity conducted its first nuclear weapons test.
-
D.
largestNuclearTest
Indicates that the subject entity conducted or is associated with the largest nuclear test (by yield or scale) within a specified context or comparison set.
-
E.
firstNuclearTestLocation
Indicates the place where an entity conducted its first nuclear test.
- 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_69e25d1de32c8190a907afe9c3d6cd6d |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1c88a4b948190989a261e79b996a6 |
completed | April 29, 2026, 8:59 a.m. |
| PD | Predicate disambiguation | batch_69f1614612b481908c45d99e588882f9 |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 8:09 p.m.