Triple
T35457
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ten Commandments |
E701
|
entity |
| Predicate | tabletContentDivision |
P2332
|
FINISHED |
| Object | first tablet focuses on relationship with God |
—
|
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: first tablet focuses on relationship with God | Statement: [Ten Commandments, tabletContentDivision, first tablet focuses on relationship with God]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tabletContentDivision Context triple: [Ten Commandments, tabletContentDivision, first tablet focuses on relationship with God]
-
A.
hasNumberOfDivisions
Indicates the relationship that specifies how many divisions or subunits an entity possesses.
-
B.
divisionTitle
Indicates the formal name or title assigned to a specific division within a larger organization or structure.
-
C.
hasDivisionLevel
Indicates that one entity is associated with a specific hierarchical or organizational division level of another entity.
-
D.
hasPart
Indicates that one entity is a component, segment, or constituent part of another entity.
-
E.
pages
Indicates that one entity consists of or contains a certain number of pages, or that a specific page-related attribute is associated with it.
- 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_69a2479dec388190967ba648663442c9 |
completed | Feb. 28, 2026, 1:40 a.m. |
| NER | Named-entity recognition | batch_69a24989c3308190af59dfae37cfc32f |
completed | Feb. 28, 2026, 1:48 a.m. |
| PD | Predicate disambiguation | batch_69a24873e97c8190b9e4279e43b6de14 |
completed | Feb. 28, 2026, 1:44 a.m. |
| PDg | Predicate description generation | batch_69a24988d4688190b4584356ed7dea50 |
completed | Feb. 28, 2026, 1:48 a.m. |
Created at: Feb. 28, 2026, 1:44 a.m.