Triple
T16906804
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hebrew letter Ayin |
E424583
|
entity |
| Predicate | hasUseInCantillation |
P67250
|
FINISHED |
| Object | yes |
—
|
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: yes | Statement: [Hebrew letter Ayin, hasUseInCantillation, yes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasUseInCantillation Context triple: [Hebrew letter Ayin, hasUseInCantillation, yes]
-
A.
hasLiturgicalTone
Indicates that something (such as a chant, text, or musical phrase) is associated with or performed in a specific liturgical tone or mode.
-
B.
usesLiturgicalMelody
Indicates that one entity employs or incorporates a specific liturgical melody in its music or performance.
-
C.
usesToneMarks
chosen
Indicates that one entity applies or includes diacritical tone marks in the representation or transcription of another entity (such as text, language, or symbols).
-
D.
usesSyllables
Indicates that one entity forms, expresses, or analyzes something by employing syllables as its basic units.
-
E.
usesTextInScore
Indicates that one entity incorporates or references a specific text within its score or scoring process.
- 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_69d889da3e8c8190a2b118f383f0beac |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e3ca39f9b08190b15106c6caf895ec |
completed | April 18, 2026, 6:15 p.m. |
| PD | Predicate disambiguation | batch_69e32b9489408190bcb2ede567ff5bf9 |
completed | April 18, 2026, 6:58 a.m. |
Created at: April 10, 2026, 5:30 a.m.