Triple
T10361329
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kam people |
E244139
|
entity |
| Predicate | inhabits |
P2574
|
FINISHED |
| Object | South Asia |
E6055
|
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: South Asia | Statement: [Kam people, inhabits, South Asia]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: South Asia Context triple: [Kam people, inhabits, South Asia]
-
A.
South Asia
chosen
South Asia is a culturally and linguistically diverse region of the Asian continent that includes countries such as India, Pakistan, Bangladesh, Nepal, Sri Lanka, Bhutan, and the Maldives.
-
B.
Eastern South Asia
Eastern South Asia is the eastern subregion of the South Asian subcontinent, generally encompassing Bangladesh, Bhutan, Nepal, and the eastern and northeastern parts of India.
-
C.
Asia
Asia is a figure in Greek mythology, often considered an Oceanid nymph associated with the region that later bore her name.
-
D.
Asia
Asia is a figure in Greek mythology, often considered one of the Oceanids and associated with the region that later bore her name.
-
E.
Asia
Asia is the world’s largest and most populous continent, encompassing diverse cultures, languages, and landscapes across the Eastern and Northern Hemispheres.
- 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_69d381b22b8c8190aaed476be5f872a9 |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4e96209548190957368ee8c6a9ec3 |
completed | April 7, 2026, 11:24 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d7953205cc8190ad7f28a7436049bc |
completed | April 9, 2026, 12:01 p.m. |
Created at: April 6, 2026, 11:59 a.m.