Triple
T7209264
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bayit Chadash |
E148755
|
entity |
| Predicate | printedTogetherWith |
P72194
|
FINISHED |
| Object | editions of Arba’ah Turim |
—
|
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: editions of Arba’ah Turim | Statement: [Bayit Chadash, printedTogetherWith, editions of Arba’ah Turim]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: printedTogetherWith Context triple: [Bayit Chadash, printedTogetherWith, editions of Arba’ah Turim]
-
A.
printedAlongside
chosen
Indicates that two items are printed together in the same context, such as on the same page, document, or output.
-
B.
printedOn
Indicates that something is produced or reproduced in physical form on a specified material, surface, or medium.
-
C.
printedBy
Indicates that one entity is produced or output in physical or digital form by another entity acting as the printer or printing agent.
-
D.
printedFor
Indicates that one entity produced a printed version of something specifically intended for another entity as the recipient or audience.
-
E.
inscribedTogetherWith
Indicates that one entity is inscribed jointly with another on the same surface, object, or document as part of a single inscription context.
- 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_69c687e8cf188190b5f3ecffd681f04e |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c6e96c46dc819080a6b40456d7b068 |
completed | March 27, 2026, 8:32 p.m. |
| PD | Predicate disambiguation | batch_69c6e75f84e481909e7866186ae80cff |
completed | March 27, 2026, 8:23 p.m. |
Created at: March 27, 2026, 2:52 p.m.