Triple
T9119252
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sanjna |
E218802
|
entity |
| Predicate | parentOf |
P120
|
FINISHED |
| Object | Yami |
E218803
|
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: Yami | Statement: [Sanjna, parentOf, Yami]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Yami Context triple: [Sanjna, parentOf, Yami]
-
A.
Yami
chosen
Yami is a figure in Hindu mythology known as the sister of the death god Yama and often associated with early Vedic narratives about sibling relationships and morality.
-
B.
Yami (Tao)
Yami (Tao) is an Austronesian language spoken by the Tao people of Orchid Island, Taiwan, known for its distinct phonology and close relation to the Batanic languages of the Philippines.
-
C.
Miya
Miya is a Japanese honorific suffix historically used in imperial and aristocratic titles, particularly within branches of the Japanese Imperial Family such as the Higashikuni-no-miya.
-
D.
Miya
Miya is a Chadic language spoken in parts of northern Nigeria, known for its complex tonal system and Afroasiatic linguistic roots.
-
E.
Marichi
Marichi is a revered Vedic sage (one of the Saptarishi) regarded as a mind-born son of Brahma and an important progenitor in Hindu cosmology.
- 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_69ca83dddd548190983b96c664f7f367 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cca8a7c6d48190a015efd17a017ca1 |
completed | April 1, 2026, 5:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d047baf5e48190aab0eb19908fabfc |
completed | April 3, 2026, 11:05 p.m. |
Created at: March 30, 2026, 7:17 p.m.