Triple
T8369496
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ông Công Ông Táo |
E197417
|
entity |
| Predicate | alsoKnownAs |
P39
|
FINISHED |
| Object | Táo Quân |
E197417
|
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: Táo Quân | Statement: [Ông Công Ông Táo, alsoKnownAs, Táo Quân]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Táo Quân Context triple: [Ông Công Ông Táo, alsoKnownAs, Táo Quân]
-
A.
Ông Công Ông Táo
chosen
Ông Công Ông Táo are household deities in Vietnamese folk belief who oversee the family’s kitchen and domestic affairs and report annually to the Jade Emperor in heaven.
-
B.
Tujia New Year
Tujia New Year is a traditional lunar celebration of the Tujia ethnic group in China, marked by ancestral worship, folk performances, and distinctive regional customs.
-
C.
Hua Zhuang
Hua Zhuang is a subway station in Beijing that serves as a terminus on the city's Line 7.
-
D.
Tien Quan Ca
Tien Quan Ca is a Vietnamese patriotic song composed by Văn Cao that later became the national anthem of Vietnam.
-
E.
Xiàogǎn
Xiàogǎn is a prefecture-level city in central China’s Hubei province, known for its historical significance and proximity to Wuhan.
- 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_69ca82f56730819080cec5d991c76f4c |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb80a400888190bef114052f3c4f76 |
completed | March 31, 2026, 8:07 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cde7d0a6d081909ffe138f80605992 |
completed | April 2, 2026, 3:51 a.m. |
Created at: March 30, 2026, 6:01 p.m.