Triple
T19864017
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tree of Life (Kabbalah) |
E477340
|
entity |
| Predicate | numberOfSefirot |
P60423
|
FINISHED |
| Object | 10 |
—
|
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: 10 | Statement: [Tree of Life (Kabbalah), numberOfSefirot, 10]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: numberOfSefirot Context triple: [Tree of Life (Kabbalah), numberOfSefirot, 10]
-
A.
hasNumberOfSephirot
chosen
Indicates the specific count of sephirot associated with or attributed to an entity.
-
B.
containsSephirah
Indicates that one entity includes or encompasses a specific sephirah as a component, aspect, or part within itself.
-
C.
relationshipToOtherSefirot
Indicates how one sefirah is connected or related to other sefirot within the overall structure or network of sefirot.
-
D.
associatedWithSephirahInSomeKabbalisticSystems
Indicates that something is linked or connected to a particular Sephirah within at least one interpretation or variant of Kabbalistic systems.
-
E.
numberOfEnneads
Indicates the count of groups of nine (enneads) associated with or contained in an entity.
- 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_69d8e51e7d948190aedbcd6c30361c39 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6589d55a88190af7d4e12c4b07739 |
completed | April 20, 2026, 4:47 p.m. |
| PD | Predicate disambiguation | batch_69e537e21d2881909b1be82f02b99d40 |
completed | April 19, 2026, 8:15 p.m. |
Created at: April 10, 2026, 1:51 p.m.