Triple
T21635396
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sorabe script |
E533945
|
entity |
| Predicate | hasPhoneticAdaptation |
P41705
|
FINISHED |
| Object | adapted to Malagasy phonology |
—
|
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: adapted to Malagasy phonology | Statement: [Sorabe script, hasPhoneticAdaptation, adapted to Malagasy phonology]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPhoneticAdaptation Context triple: [Sorabe script, hasPhoneticAdaptation, adapted to Malagasy phonology]
-
A.
hasVocalAdaptation
Indicates that an entity possesses a specialized vocal feature or modification that alters or enhances its sound production or communication.
-
B.
isPhonetic
Indicates that one entity represents the phonetic (sound-based) form or pronunciation of another entity.
-
C.
usesPhoneticSystem
chosen
Indicates that one entity employs or is based on a particular phonetic system for representing or encoding sounds.
-
D.
hasPhoneme
Indicates that a linguistic unit (such as a word or morpheme) contains or includes a particular phoneme as part of its sound structure.
-
E.
hasPhonologicalChange
Indicates a relationship where one linguistic form undergoes a change in its sound structure relative to another form or earlier state.
- 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_69e0c465ae7481908577b7209fdb2a77 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef538c5fbc8190a3316cf91f9516dc |
completed | April 27, 2026, 12:16 p.m. |
| PD | Predicate disambiguation | batch_69e69677b9c48190bf81f795aa8ad74e |
completed | April 20, 2026, 9:11 p.m. |
Created at: April 16, 2026, 6:35 p.m.