Triple
T2518953
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sinhala script |
E55476
|
entity |
| Predicate | viramaName |
P744
|
FINISHED |
| Object | hal kirīma |
—
|
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: hal kirīma | Statement: [Sinhala script, viramaName, hal kirīma]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: viramaName Context triple: [Sinhala script, viramaName, hal kirīma]
-
A.
hasVirama
Indicates that a character or script element is associated with a virama sign, typically used to suppress the inherent vowel or join consonants in abugida writing systems.
-
B.
veilName
Indicates that an entity is associated with or identified by a particular veil-related name or alias.
-
C.
nameInSanskrit
Indicates that one entity is the name or designation of another entity when expressed in the Sanskrit language.
-
D.
hasViramaSign
Indicates that a character or script element is associated with, or takes, a virama sign used to suppress the inherent vowel in abugida writing systems.
-
E.
nameOf
chosen
Indicates that one entity is the name or designation 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_69ab49e4749c8190813311efd1630f1b |
completed | March 6, 2026, 9:40 p.m. |
| NER | Named-entity recognition | batch_69abd5a33234819082ad49fa6594b6be |
completed | March 7, 2026, 7:37 a.m. |
| PD | Predicate disambiguation | batch_69abd0bf37c0819088d28b5081ba7556 |
completed | March 7, 2026, 7:16 a.m. |
Created at: March 6, 2026, 9:46 p.m.