Triple
T9132963
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Elodie Yung |
E219134
|
entity |
| Predicate | portrayed |
P1668
|
FINISHED |
| Object | Amma |
E481237
|
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: Amma | Statement: [Elodie Yung, portrayed, Amma]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Amma Context triple: [Elodie Yung, portrayed, Amma]
-
A.
Amma
chosen
Amma is a fictional female protagonist, likely a central figure in a narrative focused on a girl or woman’s experiences.
-
B.
Amma
Amma is the popular honorific nickname of J. Jayalalithaa, the influential Indian politician and long-serving Chief Minister of Tamil Nadu.
-
C.
Amma II
Amma II was a medieval monarch of the Eastern Chalukya dynasty who ruled parts of present-day Andhra Pradesh in southern India.
-
D.
Bhudevi
Bhudevi is the Hindu earth goddess and consort of Lord Vishnu, revered as the personification of the fertile, nurturing aspects of the Earth.
-
E.
Kanaka Durga
Kanaka Durga is a revered form of the Hindu goddess Durga, worshipped especially as the presiding deity of the famous hilltop temple in Vijayawada, Andhra Pradesh.
- 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_69ca83debfc0819095800583e97ab10f |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cca8db7d808190bd22b0e5a6f9c285 |
completed | April 1, 2026, 5:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d047e5ad5481909b7e62bee4d57492 |
completed | April 3, 2026, 11:06 p.m. |
Created at: March 30, 2026, 7:18 p.m.