Triple
T17619255
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Quảng Nam province |
E429665
|
entity |
| Predicate | capital |
P234
|
FINISHED |
| Object | Tam Kỳ |
—
|
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: Tam Kỳ | Statement: [Quảng Nam province, capital, Tam Kỳ]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tam Kỳ Context triple: [Quảng Nam province, capital, Tam Kỳ]
-
A.
Tam Kỳ
chosen
Tam Kỳ is a city in central Vietnam that serves as the capital of Quảng Nam Province and a regional administrative and transportation hub.
-
B.
Kong Ji
Kong Ji was a Chinese philosopher of the late Spring and Autumn period, the grandson of Confucius, traditionally regarded as the author of the Confucian classic "Doctrine of the Mean."
-
C.
Thieu
Thieu is the family name of Nguyen Van Thieu, the South Vietnamese general and president during the Vietnam War.
-
D.
Kong Mun
Kong Mun is the Cantonese name for Jiangmen, a prefecture-level city in Guangdong Province, China, known historically as a major source of overseas Chinese emigration.
-
E.
Huy Lieu
Huy Lieu is the given name of Tran Huy Lieu, a notable Vietnamese historian, writer, and revolutionary figure.
- 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_69d889e37f308190a6aa0a69daff86c7 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e46d3547d88190ae3c9ffed63133c9 |
completed | April 19, 2026, 5:50 a.m. |
Created at: April 10, 2026, 5:51 a.m.