Triple
T8859127
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ngọc Hà Street |
E210839
|
entity |
| Predicate | partOf |
P40
|
FINISHED |
| Object | Ngọc Hà Ward |
E212824
|
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: Ngọc Hà Ward | Statement: [Ngọc Hà Street, partOf, Ngọc Hà Ward]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ngọc Hà Ward Context triple: [Ngọc Hà Street, partOf, Ngọc Hà Ward]
-
A.
Ngọc Hà Ward
chosen
Ngọc Hà Ward is a residential and historically significant urban ward located within Ba Đình District in central Hanoi, Vietnam.
-
B.
Ngọc Khánh Ward
Ngọc Khánh Ward is an urban administrative subdivision of Hanoi, Vietnam, located within the central Ba Đình District.
-
C.
Quynh Mai Ward
Quynh Mai Ward is an urban administrative subdivision of Hanoi, Vietnam, located within the central Hai Bà Trưng District.
-
D.
Ngọc Lâm Ward
Ngọc Lâm Ward is an urban neighborhood in Hanoi, Vietnam, serving as the central hub of administration and services for Long Biên District.
-
E.
Quan Hoa Ward
Quan Hoa Ward is an urban administrative subdivision of Hanoi, Vietnam, located within the city's Cầu Giấy District.
- 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_69ca838bbddc8190ab546d737e5d350f |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc60e536648190ba8da1375478c24f |
completed | April 1, 2026, 12:03 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfa0b1b86481909ec0b78de043d8f8 |
completed | April 3, 2026, 11:12 a.m. |
Created at: March 30, 2026, 6:50 p.m.