Triple
T18398996
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ashwini Kumaras |
E449941
|
entity |
| Predicate | member |
P10
|
FINISHED |
| Object | Dasra |
—
|
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: Dasra | Statement: [Ashwini Kumaras, member, Dasra]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dasra Context triple: [Ashwini Kumaras, member, Dasra]
-
A.
Dasra
chosen
Dasra is a figure from Hindu mythology, often associated with divine or semi-divine beings linked to the Ashvins and celestial lineage.
-
B.
Adhara
Adhara is a bright blue-white giant star in the constellation Canis Major and one of the most luminous stars visible to the naked eye.
-
C.
Derisha
Derisha is a lexical form or word used in a linguistic context, likely representing one member of a pair of related terms alongside Perisha.
-
D.
Darsa
Darsa is a small, sparsely inhabited island in the Indian Ocean that forms part of Yemen’s remote Socotra archipelago, known for its isolation and rich marine life.
-
E.
Adasa
Adasa was an ancient town in Judea known as the site of a decisive Maccabean victory over Seleucid forces.
- 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_69d8b9fab8a8819086a9ddc0871715e0 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e518499b1481909c5de786c48faeba |
completed | April 19, 2026, 6 p.m. |
Created at: April 10, 2026, 10:46 a.m.