Triple
T19567602
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rabri Devi |
E489623
|
entity |
| Predicate | residence |
P75
|
FINISHED |
| Object | Patna |
—
|
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: Patna | Statement: [Rabri Devi, residence, Patna]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Patna Context triple: [Rabri Devi, residence, Patna]
-
A.
Patna
Patna is a village in East Ayrshire, Scotland, historically associated with coal mining and named after the city of Patna in India.
-
B.
Patna
chosen
Patna is the capital city of the Indian state of Bihar, situated along the Ganges River and known as one of the oldest continuously inhabited cities in the world.
-
C.
Kanpur
Kanpur is a major industrial city in the northern Indian state of Uttar Pradesh, historically significant as a key site of conflict during the Indian Rebellion of 1857.
-
D.
Lucknow
Lucknow is the capital city of the Indian state of Uttar Pradesh, renowned for its rich cultural heritage, refined Urdu literature, Awadhi cuisine, and elegant Mughal and colonial-era architecture.
-
E.
Lucknow
Lucknow is a small rural community in Bruce County, Ontario, Canada, known for its agricultural character and local festivals.
- 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_69d8e8dc5d8c8190a6d7bd8864f43ca0 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e63f79adf08190b1c0b008f30b0acd |
completed | April 20, 2026, 3 p.m. |
Created at: April 10, 2026, 1:42 p.m.