Triple
T9705624
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kinmen Kaoliang Liquor |
E234890
|
entity |
| Predicate | alsoKnownAs |
P39
|
FINISHED |
| Object | Kinmen Gaoliang |
E815206
|
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: Kinmen Gaoliang | Statement: [Kinmen Kaoliang Liquor, alsoKnownAs, Kinmen Gaoliang]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kinmen Gaoliang Context triple: [Kinmen Kaoliang Liquor, alsoKnownAs, Kinmen Gaoliang]
-
A.
Kinmen Kaoliang
chosen
Kinmen Kaoliang is a famous high-proof sorghum liquor from Taiwan’s Kinmen islands, renowned for its strong flavor and cultural significance.
-
B.
Kinmen
Kinmen is a group of strategically located islands governed by Taiwan (Republic of China), situated just off the coast of mainland China and known for their military history and cross-strait significance.
-
C.
Fongshan
Fongshan is a district in Kaohsiung, Taiwan, known for its historical military sites and role as a former administrative center.
-
D.
Caishikou
Caishikou is a subway station in central Beijing that serves as an important stop on the city’s urban rail network.
-
E.
Lüshun
Lüshun is a strategically important port city in northeastern China, historically known as Port Arthur and noted for its role in several major conflicts.
- 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_69ca84cc78808190a56f3402b7c139a7 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cd9da369b4819081f6ce01289ed725 |
completed | April 1, 2026, 10:35 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1eabcf3148190b25e4f816f4dcd13 |
completed | April 5, 2026, 4:53 a.m. |
Created at: March 30, 2026, 8:19 p.m.