Triple
T906881
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jabalpur |
E19567
|
entity |
| Predicate | river |
P165
|
FINISHED |
| Object | Narmada River |
E9755
|
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: Narmada River | Statement: [Jabalpur, river, Narmada River]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Narmada River Context triple: [Jabalpur, river, Narmada River]
-
A.
Narmada
chosen
Narmada is a major river in central India, revered in Hinduism and known for flowing westward into the Arabian Sea through a deep rift valley.
-
B.
Amravati
Amravati is a major city in the Vidarbha region of central India, known as an important commercial and educational center.
-
C.
Indravati
Indravati is a significant river in central India that flows through states like Chhattisgarh and Odisha before joining the Godavari River.
-
D.
Swati
Swati is a Bantu language of the Nguni group, primarily spoken in Eswatini and parts of South Africa.
-
E.
Godavari
Godavari is one of India's longest and holiest rivers, often called the "Dakshin Ganga" (Ganges of the South), flowing across central and southern India before emptying into the Bay of Bengal.
- 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_69a4939e889c8190ac148b3ac1a7f90b |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4b2cc85a08190bc8186eb9ed1fa38 |
completed | March 1, 2026, 9:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad293209648190a380175f85d6efcc |
completed | March 8, 2026, 7:45 a.m. |
Created at: March 1, 2026, 7:39 p.m.