Triple
T2292781
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tirhuta script |
E51541
|
entity |
| Predicate | hasVowelInventory |
P22962
|
FINISHED |
| Object | similar to Maithili 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: similar to Maithili phonology | Statement: [Tirhuta script, hasVowelInventory, similar to Maithili phonology]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasVowelInventory Context triple: [Tirhuta script, hasVowelInventory, similar to Maithili phonology]
-
A.
hasVowelSystem
chosen
Indicates that an entity possesses a particular system or pattern of vowel sounds (a structured set of vowel phonemes or contrasts).
-
B.
hasVowelFeature
Indicates that an entity possesses a specific vowel-related phonological or articulatory feature.
-
C.
hasVowelNotationSystem
Indicates that a writing or transcription system for a language includes a method for explicitly representing vowel sounds.
-
D.
hasPhonemicVowels
Indicates that a language or linguistic system distinguishes vowel sounds as separate phonemes that can change word meaning.
-
E.
hasNasalVowels
Indicates that the subject language or phonological system includes vowels that are produced with nasal airflow (nasalized vowels).
- 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_69a88b09c644819090b503456d96bf70 |
completed | March 4, 2026, 7:42 p.m. |
| NER | Named-entity recognition | batch_69abcd0e42248190ada33b84d75caa64 |
completed | March 7, 2026, 7 a.m. |
| PD | Predicate disambiguation | batch_69abc589295c819092989820c2b4e9d8 |
completed | March 7, 2026, 6:28 a.m. |
Created at: March 4, 2026, 7:48 p.m.