Triple
T19595631
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Phra Ram |
E470340
|
entity |
| Predicate | enemy |
P4567
|
FINISHED |
| Object | Totsakan |
—
|
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: Totsakan | Statement: [Phra Ram, enemy, Totsakan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Totsakan Context triple: [Phra Ram, enemy, Totsakan]
-
A.
Totsakan
chosen
Totsakan is the ten-headed demon king of Lanka in the Thai epic Ramakien, serving as its central villain and a key figure in Thai classical literature and performance.
-
B.
Takanot
Takanot are rabbinic enactments or decrees established to address communal needs and clarify or safeguard Jewish law within Rabbinic Judaism.
-
C.
Takaro
Takaro is a residential suburb located within the city of Palmerston North in New Zealand.
-
D.
Taketa
Taketa is a small historic city in Japan known for its scenic rural landscapes, hot springs, and castle ruins.
-
E.
Takabisha
Takabisha is a record-breaking steel roller coaster in Japan renowned for its extremely steep drop and intense thrill elements.
- 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_69d8e510024481908415c0d616fa6186 |
completed | April 10, 2026, 11:54 a.m. |
| NER | Named-entity recognition | batch_69e6407a09608190aa1df92f8c21f9e7 |
completed | April 20, 2026, 3:04 p.m. |
Created at: April 10, 2026, 1:43 p.m.