Triple
T19112858
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Samaritan Pentateuch |
E467832
|
entity |
| Predicate | containsCommandmentConcerning |
P60020
|
FINISHED |
| Object | altar on Mount Gerizim |
—
|
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: altar on Mount Gerizim | Statement: [Samaritan Pentateuch, containsCommandmentConcerning, altar on Mount Gerizim]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: containsCommandmentConcerning Context triple: [Samaritan Pentateuch, containsCommandmentConcerning, altar on Mount Gerizim]
-
A.
containsCommandment
chosen
Indicates that one entity includes or encompasses a specific commandment as part of its content or structure.
-
B.
commandmentType
Indicates the specific category or kind of commandment that an instruction or directive belongs to.
-
C.
numberOfCommandments
Indicates the total count of commandments associated with a given subject.
-
D.
commandConcerning
Indicates that one entity issues an order or directive specifically about another entity or subject.
-
E.
doctrinalConcern
Indicates a relationship where one party has a worry, objection, or issue specifically about the correctness or acceptability of another party’s doctrines or teachings.
- 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.