Triple
T12952493
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Digamsa Yantra |
E309924
|
entity |
| Predicate | relatedTo |
P37
|
FINISHED |
| Object | Rama Yantra |
E112188
|
NE 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: Rama Yantra | Statement: [Digamsa Yantra, relatedTo, Rama Yantra]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rama Yantra Context triple: [Digamsa Yantra, relatedTo, Rama Yantra]
-
A.
Rama Yantra
Rama Yantra is an astronomical instrument at Jaipur’s Jantar Mantar observatory, designed as a cylindrical structure to measure the altitude and azimuth of celestial bodies.
-
B.
Rama Yantra
chosen
Rama Yantra is a large cylindrical astronomical instrument at Jantar Mantar in New Delhi used for measuring the altitude and azimuth of celestial bodies.
-
C.
Shanku Yantra
Shanku Yantra is an ancient gnomon-based sundial instrument at Jantar Mantar in New Delhi used for measuring time and the Sun’s position.
-
D.
Disha Yantra
Disha Yantra is an astronomical instrument at Jaipur’s Jantar Mantar observatory used to determine the direction of celestial objects.
-
E.
Misra Yantra
Misra Yantra is an astronomical instrument at Jantar Mantar in New Delhi, historically used to measure time and celestial positions with high precision.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d7bdfb57a88190836b743e2825feca |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d97e1edcdc8190a702c2a5ea58cc67 |
completed | April 10, 2026, 10:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6b8dc135c819091b7708d90db25cb |
completed | May 3, 2026, 2:54 a.m. |
Created at: April 9, 2026, 5:43 p.m.