Triple
T19240583
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rama–Sugriva pact |
E481119
|
entity |
| Predicate | associatedKingdom |
P20193
|
FINISHED |
| Object | Kishkindha |
—
|
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: Kishkindha | Statement: [Rama–Sugriva pact, associatedKingdom, Kishkindha]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kishkindha Context triple: [Rama–Sugriva pact, associatedKingdom, Kishkindha]
-
A.
Kishkindha
chosen
Kishkindha is the mythical monkey kingdom ruled by Sugriva in the Indian epic Ramayana, where Rama forms an alliance with the vanara army to search for Sita.
-
B.
Kosala
Kosala is an ancient Indian kingdom in Hindu epic tradition, most prominently known as the realm ruled by Lord Rama with its capital at Ayodhya.
-
C.
Savadatti
Savadatti is a historic town in Karnataka, India, known for its ancient temples and hilltop fort.
-
D.
Singhwara
Singhwara is a town located in the Darbhanga district of the Indian state of Bihar.
-
E.
Kadaru
Kadaru is a Nubian language spoken by the Kadaru people in parts of Sudan.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e8ccb8f48190ad420098e74fb1db |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e5faf14564819085009adf822804ab |
completed | April 20, 2026, 10:07 a.m. |
Created at: April 10, 2026, 1:26 p.m.