Triple
T23923556
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | אברהם אבן עזרא |
E602282
|
entity |
| Predicate | היה בן דורו של |
P154379
|
FINISHED |
| Object | רבי יהודה הלוי |
—
|
NE NERFINISHED |
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: רבי יהודה הלוי | Statement: [אברהם אבן עזרא, היה בן דורו של, רבי יהודה הלוי]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: היה בן דורו של Context triple: [אברהם אבן עזרא, היה בן דורו של, רבי יהודה הלוי]
-
A.
designatesGenerationOf
Indicates that one entity formally assigns or specifies another entity as the generation or creation of something (e.g., a document, product, or version).
-
B.
partOfGeneration
Indicates that one entity is a component, member, or subset of a particular generation or generational group associated with another entity.
-
C.
influencedGenerationOf
Indicates that one entity played a causal or shaping role in bringing about, inspiring, or contributing to the creation or emergence of another entity.
-
D.
generationOf
Indicates that one entity is the origin, creator, or producer of another entity.
-
E.
livedInEra
Indicates that an entity existed or was active during a particular historical era or time period.
- 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_69e2953b928c819095395fa87baca583 |
completed | April 17, 2026, 8:16 p.m. |
| NER | Named-entity recognition | batch_69f1cf1abd148190a8393418ed965019 |
completed | April 29, 2026, 9:27 a.m. |
| PD | Predicate disambiguation | batch_69f16151ebdc819086e9e1d7cc1f4f3c |
completed | April 29, 2026, 1:39 a.m. |
| PDg | Predicate description generation | batch_69f16e348b548190b76e50f9b611f76d |
completed | April 29, 2026, 2:34 a.m. |
Created at: April 17, 2026, 8:41 p.m.