Triple
T19652051
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Krong Reap |
E471838
|
entity |
| Predicate | opposes |
P437
|
FINISHED |
| Object | Neang Seda |
—
|
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: Neang Seda | Statement: [Krong Reap, opposes, Neang Seda]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Neang Seda Context triple: [Krong Reap, opposes, Neang Seda]
-
A.
Neang Seda
chosen
Neang Seda is the Khmer adaptation of Sita, the virtuous heroine and central female figure in Cambodia’s Reamker epic, derived from the Indian Ramayana.
-
B.
Neak Pean
Neak Pean is a small 12th-century Buddhist temple on an artificial island in Cambodia, famed for its central pond and surrounding pools that were likely used for ritual purification.
-
C.
Nage-Keo
Nage-Keo is an Austronesian language spoken by the Nage and Keo peoples on the island of Flores in Indonesia.
-
D.
Boun Oum
Boun Oum was a Laotian prince and conservative political leader who served multiple times as prime minister during the Kingdom of Laos era in the mid-20th century.
-
E.
Anlong Veng
Anlong Veng is a remote district in northern Cambodia known as the last stronghold of the Khmer Rouge and the place where its leader Pol Pot died.
- 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_69d8e51395348190ac1416d46dfc6db0 |
completed | April 10, 2026, 11:54 a.m. |
| NER | Named-entity recognition | batch_69e64141f61c819098fe148581fb1747 |
completed | April 20, 2026, 3:07 p.m. |
Created at: April 10, 2026, 1:44 p.m.