Triple
T3252082
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | תמוז |
E68204
|
entity |
| Predicate | מקביל בקירוב |
P1868
|
FINISHED |
| Object | יוני |
—
|
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: יוני | Statement: [תמוז, מקביל בקירוב, יוני]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: מקביל בקירוב Context triple: [תמוז, מקביל בקירוב, יוני]
-
A.
near
Indicates that one entity is located at a short distance from another entity in space or position.
-
B.
parvorder
Indicates a taxonomic relationship where one entity is classified as a parvorder, a rank below infraorder and above superfamily, within the biological hierarchy.
-
C.
hasCompanionBook
Indicates that one entity (typically a primary work) is associated with another entity that serves as its companion book, providing supplementary or related content.
-
D.
liesBeyond
Indicates that one entity is located at a greater distance or outside the boundary of another reference point, region, or limit.
-
E.
parallels
chosen
Indicates that one entity runs alongside or corresponds to another in a way that maintains a consistent separation or similarity without intersecting.
- 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_69ad858f74408190bcbd07f967cd7bd0 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69adaf440bb88190a2450405afae7f1f |
completed | March 8, 2026, 5:17 p.m. |
| PD | Predicate disambiguation | batch_69ada41ae74081909a0d1d696be8e35e |
completed | March 8, 2026, 4:30 p.m. |
Created at: March 8, 2026, 3:09 p.m.