Triple
T28555012
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bagrut |
E722980
|
entity |
| Predicate | passingMark |
P138567
|
FINISHED |
| Object | 55 |
—
|
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: 55 | Statement: [Bagrut, passingMark, 55]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: passingMark Context triple: [Bagrut, passingMark, 55]
-
A.
passMark
chosen
Indicates that an entity has achieved a score or performance level that meets or exceeds the required threshold for passing.
-
B.
passesOnSubject
Indicates that one entity transfers or conveys a subject (such as information, responsibility, or an item) from itself to another entity.
-
C.
passedExam
Indicates that an entity has successfully met the required criteria to pass a particular exam.
-
D.
passed
Indicates that one entity successfully transferred control, responsibility, or an item (such as an object, message, or test) to another entity or through a specified stage or condition.
-
E.
passFailBasis
Indicates that an outcome, evaluation, or decision is determined solely on a pass-or-fail basis rather than using a graded or ranked scale.
- 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_69f01a60204481909af1bb76247b8221 |
completed | April 28, 2026, 2:24 a.m. |
| NER | Named-entity recognition | batch_69f6504eaa908190981422fe811a100e |
completed | May 2, 2026, 7:28 p.m. |
| PD | Predicate disambiguation | batch_69f64cb0d8008190912e1430cfaf92aa |
completed | May 2, 2026, 7:12 p.m. |
Created at: April 28, 2026, 3:45 a.m.