Triple
T19112837
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Samaritan Pentateuch |
E467832
|
entity |
| Predicate | typeOfDifferences |
P61682
|
FINISHED |
| Object | orthographic variants |
—
|
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: orthographic variants | Statement: [Samaritan Pentateuch, typeOfDifferences, orthographic variants]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfDifferences Context triple: [Samaritan Pentateuch, typeOfDifferences, orthographic variants]
-
A.
differIn
chosen
Indicates that two entities are not the same in at least one specified aspect, attribute, or value.
-
B.
adaptationDifference
Indicates a difference or change in how two entities adapt or have adapted relative to each other.
-
C.
differenceDescription
Indicates a textual explanation that characterizes how two entities differ from each other.
-
D.
designDifferenceFrom
Indicates a relationship where one design is distinguished from another by specific differing features, characteristics, or structure.
-
E.
typeOfDiscrimination
Indicates a relationship where one party is subjected to a specific kind or category of discriminatory treatment by another party or within a given 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_69d8dd06a26481908039e2a1bae8c597 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e39553708190b64e24e1d190833e |
completed | April 20, 2026, 8:28 a.m. |
| PD | Predicate disambiguation | batch_69e4b9ac41848190afd0f33b42cebe99 |
completed | April 19, 2026, 11:17 a.m. |
Created at: April 10, 2026, 12:05 p.m.