Triple
T21999067
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sundargarh division of Odisha |
E543277
|
entity |
| Predicate | hasMajorCity |
P316
|
FINISHED |
| Object | Rourkela |
—
|
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: Rourkela | Statement: [Sundargarh division of Odisha, hasMajorCity, Rourkela]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rourkela Context triple: [Sundargarh division of Odisha, hasMajorCity, Rourkela]
-
A.
Bhilai
Bhilai is an industrial city in central India best known for its large steel plant and planned urban infrastructure.
-
B.
Rourkela industrial region
chosen
Rourkela industrial region is a major steel and engineering hub in eastern India, centered around the Rourkela Steel Plant and associated heavy industries.
-
C.
Jamshedpur
Jamshedpur is a major industrial city in eastern India, best known as the home of Tata Steel and one of the country’s earliest planned company towns.
-
D.
Bilaspur
Bilaspur is a major city in the Indian state of Chhattisgarh, known as an important administrative, commercial, and judicial center.
-
E.
Bilaspur
Bilaspur is a town in the Yamunanagar district of Haryana, India, known as a local commercial and administrative center for surrounding rural areas.
- 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_69e11e2c814c8190837d072789000486 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f12768c0088190b0c8d5cd9b7bf710 |
completed | April 28, 2026, 9:32 p.m. |
Created at: April 16, 2026, 8:19 p.m.