Triple
T22476365
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Delhi–Meerut–Saharanpur line |
E555639
|
entity |
| Predicate | endPoint |
P390
|
FINISHED |
| Object | Saharanpur |
—
|
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: Saharanpur | Statement: [Delhi–Meerut–Saharanpur line, endPoint, Saharanpur]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Saharanpur Context triple: [Delhi–Meerut–Saharanpur line, endPoint, Saharanpur]
-
A.
Saharanpur
chosen
Saharanpur is a city in the Indian state of Uttar Pradesh known as a commercial and transportation hub, particularly for its wood carving industry and agricultural trade.
-
B.
Sirsa
Sirsa is a city in the Indian state of Haryana, known as a regional commercial and administrative center near the Rajasthan and Punjab borders.
-
C.
Ambala
Ambala is a historic city and important military and transportation hub in the northern Indian state of Haryana.
-
D.
Khurja
Khurja is a town in Uttar Pradesh, India, renowned for its traditional ceramic and pottery industry.
-
E.
Rampur
Rampur is a small settlement located on Middle Andaman Island in the Andaman and Nicobar Islands of India.
- 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_69e11e52c2048190952dc5df209b9bed |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15be48cec8190baff90f8566a85d0 |
completed | April 29, 2026, 1:16 a.m. |
Created at: April 16, 2026, 8:49 p.m.