Triple
T189376
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sanskrit |
E3683
|
entity |
| Predicate | grammaticalFeature |
P662
|
FINISHED |
| Object | eight grammatical cases |
—
|
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: eight grammatical cases | Statement: [Sanskrit, grammaticalFeature, eight grammatical cases]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: grammaticalFeature Context triple: [Sanskrit, grammaticalFeature, eight grammatical cases]
-
A.
grammaticalStructure
Indicates the way linguistic elements are organized and related within a sentence or phrase according to grammatical rules.
-
B.
hasGrammaticalGender
Indicates that one entity assigns or possesses a specific grammatical gender in relation to another entity (such as a word, phrase, or linguistic unit).
-
C.
characterizedBy
chosen
Indicates that one entity possesses a defining quality, feature, or attribute expressed by another entity.
-
D.
hasStressPattern
Indicates that an entity (such as a word or phrase) follows a particular arrangement of stressed and unstressed units (e.g., syllables) in its pronunciation.
-
E.
hasPhonemicContrast
Indicates that two or more speech sounds are distinguished in a language by differences that change word meaning.
- 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_69a2548debd48190ae3a06d6e65b53c6 |
completed | Feb. 28, 2026, 2:35 a.m. |
| NER | Named-entity recognition | batch_69a2594c385481909e1e088e45c460a4 |
completed | Feb. 28, 2026, 2:56 a.m. |
| PD | Predicate disambiguation | batch_69a25672332081909386f35f3ca15dd2 |
completed | Feb. 28, 2026, 2:44 a.m. |
Created at: Feb. 28, 2026, 2:41 a.m.