Triple
T20930960
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arabic mutaqārib metre |
E515467
|
entity |
| Predicate | hasNumberOfFeetPerVerse |
P62939
|
FINISHED |
| Object | eight feet per full verse |
—
|
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 feet per full verse | Statement: [Arabic mutaqārib metre, hasNumberOfFeetPerVerse, eight feet per full verse]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNumberOfFeetPerVerse Context triple: [Arabic mutaqārib metre, hasNumberOfFeetPerVerse, eight feet per full verse]
-
A.
typicalFootCountPerHemistich
chosen
Indicates the usual number of metrical feet found in each hemistich (half-line) of a verse.
-
B.
hasVerseCount
Indicates that an entity (such as a text or section) is associated with a specific number of verses it contains.
-
C.
approximateNumberOfVerses
Indicates an estimated or approximate count of verses associated with an entity.
-
D.
hasVerseStyle
Indicates that one entity is characterized by, or presented in, the verse style specified by another entity.
-
E.
hasVerseRange
Indicates a relationship where a text or passage is associated with a specific contiguous range of verses it spans.
- 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_69e0b4fb431c8190b9d40e6a72f0cc87 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6f6557e4881909ce932c3f538304a |
completed | April 21, 2026, 4 a.m. |
| PD | Predicate disambiguation | batch_69e5c9af1fe08190953366a466950140 |
completed | April 20, 2026, 6:37 a.m. |
Created at: April 16, 2026, 12:49 p.m.