Triple
T802244
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cambodia |
E17153
|
entity |
| Predicate | writingSystem |
P454
|
FINISHED |
| Object | Khmer script |
E41507
|
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: Khmer script | Statement: [Cambodia, writingSystem, Khmer script]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Khmer script Context triple: [Cambodia, writingSystem, Khmer script]
-
A.
Khmer script
chosen
Khmer script is an abugida writing system used primarily for the Khmer language of Cambodia, characterized by its intricate consonant and vowel symbols derived from the ancient Brahmi script.
-
B.
Lao script
Lao script is an abugida writing system of the Tai-Kadai language family, primarily used to write the Lao language and closely related to the Thai script.
-
C.
Burmese script
The Burmese script is an abugida used for writing the Burmese language and several other languages of Myanmar, characterized by its rounded letters and Indic origins.
-
D.
Mon-Khmer
Mon-Khmer is a major branch of the Austroasiatic language family that includes numerous languages spoken across mainland Southeast Asia and parts of South Asia.
-
E.
Balinese script
Balinese script is an abugida used primarily on the Indonesian island of Bali for writing the Balinese language, as well as liturgical and historical texts in Sanskrit and Old Javanese.
- 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_69a49378b9c48190adbf5f62e5b7aca1 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4aa9e0f0081909d2a89387d6c08e1 |
completed | March 1, 2026, 9:07 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a76d818e208190a8f3b165c0770e09 |
completed | March 3, 2026, 11:23 p.m. |
Created at: March 1, 2026, 7:38 p.m.