Triple
T697466
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Reginald Dyer |
E13922
|
entity |
| Predicate | placeOfEvent |
P373
|
FINISHED |
| Object | Amritsar |
E23792
|
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: Amritsar | Statement: [Reginald Dyer, placeOfEvent, Amritsar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Amritsar Context triple: [Reginald Dyer, placeOfEvent, Amritsar]
-
A.
Amritsar
chosen
Amritsar is a historic city in the Indian state of Punjab, renowned as the spiritual center of Sikhism and home to the Golden Temple.
-
B.
Chandigarh
Chandigarh is a planned city in northern India, renowned for its modernist architecture and urban design largely conceived by the Swiss-French architect Le Corbusier.
-
C.
Jammu
Jammu is a historically significant city and region in northern India, known as the winter capital of Jammu and Kashmir and a former stronghold of Dogra rulers.
-
D.
Aligarh
Aligarh is a prominent city in northern India known for its lock industry and as the home of Aligarh Muslim University.
-
E.
Rawalpindi
Rawalpindi is a major city in Pakistan’s Punjab province, historically significant as a former temporary national capital and now a key commercial and military center.
- 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_69a493406c408190957eeec9048a8fb6 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a0c8055881909565ebde2be8fd7a |
completed | March 1, 2026, 8:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a7b8341cf0819089d18c2c63192679 |
completed | March 4, 2026, 4:42 a.m. |
Created at: March 1, 2026, 7:36 p.m.