Triple
T5200379
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vayu |
E117377
|
entity |
| Predicate | consort |
P13
|
FINISHED |
| Object | Bharati |
E109929
|
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: Bharati | Statement: [Vayu, consort, Bharati]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bharati Context triple: [Vayu, consort, Bharati]
-
A.
Bharati
chosen
Bharati is an epithet of the Hindu goddess Saraswati, highlighting her role as the divine embodiment of eloquence, learning, and the arts.
-
B.
Indi
Indi is an Australian federal electoral division in the state of Victoria, encompassing a largely rural and regional area in the state's northeast.
-
C.
Orya
Orya is the ISO 15924 script code representing the Odia script used for writing the Odia language of eastern India.
-
D.
Mehri
Mehri is a Modern South Arabian language spoken primarily by the Mehri people in eastern Yemen and western Oman, known for preserving many archaic Semitic features.
-
E.
Usha
Usha is a goddess in Hindu mythology, often associated with the dawn and revered as a radiant divine figure.
- 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_69bd4462ed04819084fcb01eb9d2fa74 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd7a209d7c81908fa0d3bf2c482a34 |
completed | March 20, 2026, 4:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bee0a37d8c8190842de23da26dd2cb |
completed | March 21, 2026, 6:17 p.m. |
Created at: March 20, 2026, 1:47 p.m.