Triple
T27146818
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | נצרת עילית |
E681971
|
entity |
| Predicate | מדיניות תכנון |
P71686
|
FINISHED |
| Object | עיר יהודית צמודה לנצרת הערבית |
—
|
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: עיר יהודית צמודה לנצרת הערבית | Statement: [נצרת עילית, מדיניות תכנון, עיר יהודית צמודה לנצרת הערבית]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: מדיניות תכנון Context triple: [נצרת עילית, מדיניות תכנון, עיר יהודית צמודה לנצרת הערבית]
-
A.
planningPolicy
chosen
Indicates that one entity establishes or defines rules, guidelines, or strategies governing how another entity should plan or make planning-related decisions.
-
B.
planning
Indicates that an entity is engaged in organizing or devising a future action, event, or course of behavior involving another entity or entities.
-
C.
planningNation
Indicates that a nation is responsible for planning, organizing, or coordinating the referenced activity, event, or operation.
-
D.
plan
Indicates that an entity intends or arranges for a future action or sequence of actions to occur.
-
E.
policyConcept
Indicates that one entity is a policy and the other is a conceptual element or idea that defines, characterizes, or underlies that policy.
- 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_69eefacca3888190b67238d380e8f28b |
completed | April 27, 2026, 5:57 a.m. |
| NER | Named-entity recognition | batch_69f624c6dff08190ba0573eba9d63449 |
completed | May 2, 2026, 4:22 p.m. |
| PD | Predicate disambiguation | batch_69f61b40f02081909bd9c3ea73249163 |
completed | May 2, 2026, 3:41 p.m. |
Created at: April 27, 2026, 9:11 a.m.