Triple
T8917349
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Feast of the Seven Fishes |
E212324
|
entity |
| Predicate | courseCountVariability |
P86377
|
FINISHED |
| Object | number of seafood dishes varies by family |
—
|
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: number of seafood dishes varies by family | Statement: [Feast of the Seven Fishes, courseCountVariability, number of seafood dishes varies by family]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: courseCountVariability Context triple: [Feast of the Seven Fishes, courseCountVariability, number of seafood dishes varies by family]
-
A.
numberOfCourses
Indicates the quantity of courses associated with a given entity.
-
B.
courseLength
Indicates the duration or total length of a course, typically measured in units such as hours, weeks, or credits.
-
C.
courseShape
Indicates the geometric layout or configuration that defines the path or outline of a course.
-
D.
hasMultipleCourses
Indicates that an entity is associated with more than one course within the given context.
-
E.
courseType
Indicates the classification or category of a course based on its nature, level, or instructional format.
- F. None of above. chosen
Provenance (4 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_69ca8393b1808190bd4336787ffa2c40 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc66120eb08190913ab6c42f26ffb8 |
completed | April 1, 2026, 12:25 a.m. |
| PD | Predicate disambiguation | batch_69cc5ed0ef3c81908cc69eac852ee12a |
completed | March 31, 2026, 11:54 p.m. |
| PDg | Predicate description generation | batch_69cc600a59708190ae426044bbcd7929 |
completed | April 1, 2026, midnight |
Created at: March 30, 2026, 6:56 p.m.