Triple
T13020633
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bhagandeshwara Temple |
E326160
|
entity |
| Predicate | deity |
P5606
|
FINISHED |
| Object | Subramanya |
E164754
|
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: Subramanya | Statement: [Bhagandeshwara Temple, deity, Subramanya]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Subramanya Context triple: [Bhagandeshwara Temple, deity, Subramanya]
-
A.
Subramanya
chosen
Subramanya is a Hindu deity of war and wisdom, widely revered in South India and identified with the god Kartikeya (Murugan).
-
B.
Ananthabhadram
Ananthabhadram is a 2005 Malayalam-language fantasy horror film known for its visually rich storytelling and memorable performances.
-
C.
Dasaratha
Dasaratha is the legendary king of Ayodhya in the Hindu epic Ramayana and the father of Lord Rama.
-
D.
Kailasam
Kailasam is the given name of renowned Indian filmmaker and playwright K. Balachander, a major figure in Tamil cinema and theatre.
-
E.
Neeladri
Neeladri is one of the sacred hills that form part of the Tirumala hill range associated with the Tirumala Venkateswara Temple in Andhra Pradesh, India.
- 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_69d8076cc45c81908123123f43e69266 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69d97ecf21bc819082fb512bc479b4be |
completed | April 10, 2026, 10:50 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6c119e19c81908ae2b1caff6f2f32 |
completed | May 3, 2026, 3:29 a.m. |
Created at: April 9, 2026, 8:51 p.m.