Triple
T20179995
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hill Tracts of Chittagong |
E492701
|
entity |
| Predicate | ethnicGroup |
P194
|
FINISHED |
| Object | Marma |
—
|
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: Marma | Statement: [Hill Tracts of Chittagong, ethnicGroup, Marma]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marma Context triple: [Hill Tracts of Chittagong, ethnicGroup, Marma]
-
A.
Marma
chosen
The Marma are an indigenous ethnic group of Buddhist heritage primarily inhabiting the hilly regions of southeastern Bangladesh, especially in the Chittagong Hill Tracts.
-
B.
Marma
Marma is a small locality in Älvkarleby Municipality in Uppsala County, Sweden.
-
C.
Marhaura
Marhaura is a prominent town in Bihar, India, known historically as an industrial and commercial center within the Saran region.
-
D.
Baghmara
Baghmara is a town in the South Garo Hills district of Meghalaya, India, known as a gateway to nearby forests, caves, and wildlife areas.
-
E.
Bhailsa
Bhailsa is the former historical name of Vidisha, an ancient city in the central Indian state of Madhya Pradesh known for its rich archaeological and cultural heritage.
- 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_69da6268a034819081cbd9ea5a1c9475 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e668edf27881909820f9103e72533e |
completed | April 20, 2026, 5:57 p.m. |
Created at: April 11, 2026, 11:36 p.m.