Triple
T19608736
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kali Bein |
E470673
|
entity |
| Predicate | flowsThrough |
P225
|
FINISHED |
| Object | Sultanpur Lodhi |
—
|
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: Sultanpur Lodhi | Statement: [Kali Bein, flowsThrough, Sultanpur Lodhi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sultanpur Lodhi Context triple: [Kali Bein, flowsThrough, Sultanpur Lodhi]
-
A.
Sultanpur Lodhi
chosen
Sultanpur Lodhi is a historic town in Punjab, India, renowned as a major Sikh pilgrimage site associated with Guru Nanak Dev Ji.
-
B.
Dabwali
Dabwali is a town and legislative assembly constituency located in the Sirsa district of the northern Indian state of Haryana.
-
C.
Randhawa
Randhawa is an Indian-origin Punjabi surname notably borne by American politician Nikki Haley.
-
D.
Haidergarh
Haidergarh is a town in the Barabanki district of Uttar Pradesh, India, known for its local markets and agricultural surroundings.
-
E.
Barwala
Barwala is a prominent town in the Hisar 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_69d8e510fa248190b7afb274a1d4cf73 |
completed | April 10, 2026, 11:54 a.m. |
| NER | Named-entity recognition | batch_69e640c964fc8190bd1cb60f4b233eaa |
completed | April 20, 2026, 3:05 p.m. |
Created at: April 10, 2026, 1:43 p.m.