Triple
T12555977
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Karen script |
E295216
|
entity |
| Predicate | hasDistinctLettersFrom |
P33153
|
FINISHED |
| Object | Burmese script |
E83193
|
NE FINISHED |
How this triple was built (3 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: Burmese script | Statement: [Karen script, hasDistinctLettersFrom, Burmese script]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Burmese script Context triple: [Karen script, hasDistinctLettersFrom, Burmese script]
-
A.
Burmese script
chosen
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.
-
B.
Tai Tham script
The Tai Tham script is an ancient Brahmic-derived writing system used primarily for religious and literary texts in several Tai languages of northern Southeast Asia, including Lanna (Northern Thai), Tai Lue, and Khün.
-
C.
Hmong Thai script
Hmong Thai script is an orthographic system used in Thailand to write the Hmong language, serving as an alternative to Romanized writing systems.
-
D.
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.
-
E.
Lontara script
The Lontara script is an indigenous writing system traditionally used by the Bugis and Makassarese peoples of South Sulawesi, Indonesia, to write their Austronesian languages.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDistinctLettersFrom Context triple: [Karen script, hasDistinctLettersFrom, Burmese script]
-
A.
hasDistinctLettersFor
chosen
Indicates that one entity is associated with another such that the letters used in the first are all different from (i.e., share no letters with) those used in the second.
-
B.
hasDistinctLetters
Indicates that all letters in the given string or word are unique, with no character repeated.
-
C.
hasDistinctCharacterSet
Indicates that two compared items use different sets of characters, with no character set being a subset or duplicate of the other.
-
D.
hasDistinctVowelLetters
Indicates that the subject contains vowel letters that are all different from one another, with no vowel repeated.
-
E.
hasLettersFor
Indicates that one entity possesses or contains written correspondence intended for another entity.
- F. None of above.
Provenance (4 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_69d6ad9cac2c81908e8a7bed82d1e21d |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d95f5507b481908d13cc317b7402f6 |
completed | April 10, 2026, 8:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f65eb538388190b9fb78306fbab2f3 |
completed | May 2, 2026, 8:29 p.m. |
| PD | Predicate disambiguation | batch_69d95410d0b0819097646edd1b837104 |
completed | April 10, 2026, 7:48 p.m. |
Created at: April 8, 2026, 11:47 p.m.