Triple
T19405317
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mandla Lok Sabha constituency |
E485438
|
entity |
| Predicate | hasLanguage |
P15
|
FINISHED |
| Object | Gondi |
—
|
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: Gondi | Statement: [Mandla Lok Sabha constituency, hasLanguage, Gondi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gondi Context triple: [Mandla Lok Sabha constituency, hasLanguage, Gondi]
-
A.
Gondi
chosen
Gondi is a Dravidian language spoken primarily by the Gondi people in central India, especially across parts of Madhya Pradesh, Maharashtra, Chhattisgarh, and neighboring regions.
-
B.
Oda
Oda is a town located in the Eastern Region of Ghana, known for its role as a local commercial and administrative center.
-
C.
Oda
Oda is a Japanese samurai clan most famously associated with the powerful 16th-century warlord Oda Nobunaga, a key figure in the unification of Japan.
-
D.
Oda
Oda was a medieval noblewoman best known as the mother of Bernard I, Duke of Saxony, and a member of the influential Saxon aristocracy.
-
E.
Gotō
Gotō is a Japanese surname borne by various notable figures in politics, business, and the arts.
- 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_69d8e8d5162481909db12435d9535c1a |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e6257a361c8190bf019fc350faa225 |
completed | April 20, 2026, 1:09 p.m. |
Created at: April 10, 2026, 1:36 p.m.