Triple
T7426200
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chaleo Yoovidhya |
E171373
|
entity |
| Predicate | associatedBrand |
P1500
|
FINISHED |
| Object | Krating Daeng |
E663373
|
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: Krating Daeng | Statement: [Chaleo Yoovidhya, associatedBrand, Krating Daeng]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Krating Daeng Context triple: [Chaleo Yoovidhya, associatedBrand, Krating Daeng]
-
A.
Krating Daeng
chosen
Krating Daeng is a Thai energy drink that served as the inspiration and original formula behind the globally popular Red Bull brand.
-
B.
Wat Plai Laem
Wat Plai Laem is a colorful Buddhist temple complex on Ko Samui in Thailand, renowned for its large statues of Guanyin and the Laughing Buddha set beside a scenic lake.
-
C.
Chintara Sukapatana
Chintara Sukapatana is a Thai actress best known internationally for her role in the film "Good Morning, Vietnam."
-
D.
Phra Lak
Phra Lak is a key heroic figure in Thai mythology, known as the loyal younger brother and companion of Phra Ram in the Ramakien epic.
-
E.
Phra Ram
Phra Ram is the heroic central figure in the Thai epic Ramakien, revered as a righteous prince and incarnation of the god Vishnu.
- 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_69c68a625d048190af70eb8b63bec5a0 |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f303eb988190ba9df7946fce1c86 |
completed | March 27, 2026, 9:13 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c8277f749c8190a91f620c71c48433 |
completed | March 28, 2026, 7:09 p.m. |
Created at: March 27, 2026, 3:12 p.m.