Triple
T21985027
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hangul Syllables |
E542934
|
entity |
| Predicate | decomposesTo |
P73433
|
FINISHED |
| Object | Hangul Jamo sequences |
—
|
LITERAL 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: Hangul Jamo sequences | Statement: [Hangul Syllables, decomposesTo, Hangul Jamo sequences]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: decomposesTo Context triple: [Hangul Syllables, decomposesTo, Hangul Jamo sequences]
-
A.
decomposesIn
Indicates that one entity breaks down or separates into another entity or set of entities as its components or products.
-
B.
hasDecomposition
chosen
Indicates that something can be broken down or separated into constituent parts, components, or simpler elements.
-
C.
decomposesAbove
Indicates that one entity breaks down or disintegrates into parts or components that are located spatially above another entity.
-
D.
decompositionType
Indicates the specific way in which a whole is broken down into its constituent parts or components.
-
E.
yieldsDecomposition
Indicates that one entity produces or results in a particular breakdown or decomposition of another entity.
- F. None of above.
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_69e0c48136b081908831fa907cc02e18 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f12708cdcc81909511d9f81bd8f20e |
completed | April 28, 2026, 9:30 p.m. |
| PD | Predicate disambiguation | batch_69e6f6154e408190acc5b2c278acaff4 |
completed | April 21, 2026, 3:59 a.m. |
Created at: April 16, 2026, 8:04 p.m.