Triple
T19309999
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kalkaji Mandir |
E482938
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Okhla |
—
|
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: Okhla | Statement: [Kalkaji Mandir, near, Okhla]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Okhla Context triple: [Kalkaji Mandir, near, Okhla]
-
A.
Okhla
chosen
Okhla is a locality in South Delhi, India, known for its industrial areas, residential colonies, and proximity to the Yamuna River.
-
B.
Kharela
Kharela is a rural village located in the Mahoba district of Uttar Pradesh, India.
-
C.
Karwi
Karwi is a town in Uttar Pradesh, India, known primarily as the rail and road gateway to the historic hill fort of Kalinjar.
-
D.
Mehsana
Mehsana is a prominent city in the Indian state of Gujarat, known for its dairy industry, oil and natural gas fields, and historical temples.
-
E.
Haldi
Haldi is the chief war and national god of the ancient Kingdom of Urartu, central to its state religion and royal ideology.
- 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_69d8e8d04d5c8190baa816986f2b1d1e |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e604cc62e08190b5ba5dfc44efdc5c |
completed | April 20, 2026, 10:49 a.m. |
Created at: April 10, 2026, 1:32 p.m.