Triple
T152818
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sabarmati Ashram |
E3466
|
entity |
| Predicate | city |
P40
|
FINISHED |
| Object | Ahmedabad |
E14357
|
NE FINISHED |
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: Ahmedabad | Statement: [Sabarmati Ashram, city, Ahmedabad]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ahmedabad Context triple: [Sabarmati Ashram, city, Ahmedabad]
-
A.
Ahmedabad
chosen
Ahmedabad is a major city in the western Indian state of Gujarat, known for its rich history, textile industry, and role as an important economic and cultural center.
-
B.
Rajkot
Rajkot is a major city in the Indian state of Gujarat, known as an important commercial and cultural center of the Saurashtra region.
-
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.
Mumbai
Mumbai is a densely populated coastal metropolis in western India that serves as the country’s financial hub and the center of its film industry, Bollywood.
-
E.
Nagpur
Nagpur is a major city in the Indian state of Maharashtra, known as a key political and commercial center and often referred to as the "Orange City" for its famous orange production.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69a252868de4819080e21c9938bfe8b6 |
completed | Feb. 28, 2026, 2:27 a.m. |
| NER | Named-entity recognition | batch_69a25810799c8190a515a39169126e46 |
completed | Feb. 28, 2026, 2:50 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a34418bb848190ac26adef7f990f93 |
completed | Feb. 28, 2026, 7:38 p.m. |
Created at: Feb. 28, 2026, 2:31 a.m.