Triple
T20354586
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kishkindha |
E496107
|
entity |
| Predicate | associatedCharacter |
P12208
|
FINISHED |
| Object | Angada |
—
|
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: Angada | Statement: [Kishkindha, associatedCharacter, Angada]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Angada Context triple: [Kishkindha, associatedCharacter, Angada]
-
A.
Angada
chosen
Angada is a heroic Vanara prince in the Indian epic Ramayana, renowned for his loyalty to Rama and his role in the war against Ravana.
-
B.
Kalahandi
Kalahandi is a district in the Indian state of Odisha, known for its agrarian economy, tribal population, and history of both rich cultural heritage and severe drought-related poverty.
-
C.
Nikaweratiya
Nikaweratiya is a town in Sri Lanka’s North Western Province known for its agricultural surroundings and role as a local commercial center.
-
D.
Tanguturi
Tanguturi is the given name of T. Prakasam, a prominent Indian freedom fighter and former Chief Minister of the Madras Presidency and Andhra State.
-
E.
Bhailsa
Bhailsa is the former historical name of Vidisha, an ancient city in the central Indian state of Madhya Pradesh known for its rich archaeological and cultural heritage.
- 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_69e0b4a3f7f48190b37f354574028ca6 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e67852ca9881908a5af18005639859 |
completed | April 20, 2026, 7:02 p.m. |
Created at: April 16, 2026, 11:25 a.m.