Triple
T6713691
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ram Mandir, Ayodhya |
E153209
|
entity |
| Predicate | hasShikhara |
P30743
|
FINISHED |
| Object | main shikhara over sanctum |
—
|
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: main shikhara over sanctum | Statement: [Ram Mandir, Ayodhya, hasShikhara, main shikhara over sanctum]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasShikhara Context triple: [Ram Mandir, Ayodhya, hasShikhara, main shikhara over sanctum]
-
A.
hasGhat
Indicates that a place or location possesses or is associated with a ghat (a series of steps or landing area leading to a body of water).
-
B.
hasGhatCount
Indicates the number of ghats associated with a given entity.
-
C.
hasRaga
Indicates that something (such as a musical piece, performance, or composition) is associated with or based on a specific raga.
-
D.
isPancharangaKshetram
Indicates that a temple or sacred site is recognized as one of the Pancharanga Kshetrams, the five traditional holy shrines dedicated to Lord Ranganatha (Vishnu) along the Kaveri river.
-
E.
hasDomeOrSpire
chosen
Indicates that one entity possesses or features a dome or spire as part of its structure.
- 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_69c68809b4608190a2509ddb5ab87f05 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d122d6cc81909bde0c94fb95f016 |
completed | March 27, 2026, 6:49 p.m. |
| PD | Predicate disambiguation | batch_69c6d08c5d348190a29dee668c398e70 |
completed | March 27, 2026, 6:46 p.m. |
Created at: March 27, 2026, 2:07 p.m.