Triple
T37945032
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | קו ירוק |
E946581
|
entity |
| Predicate | שימש בסיס ל |
P2909
|
FINISHED |
| Object | גבולות השיח המדיני על פתרון שתי המדינות |
—
|
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: גבולות השיח המדיני על פתרון שתי המדינות | Statement: [קו ירוק, שימש בסיס ל, גבולות השיח המדיני על פתרון שתי המדינות]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: שימש בסיס ל Context triple: [קו ירוק, שימש בסיס ל, גבולות השיח המדיני על פתרון שתי המדינות]
-
A.
بنیاد
Indicates that an entity establishes, founds, or sets up another entity, such as an institution, organization, or structure.
-
B.
sisterBase
Indicates that one entity is the sister of another, sharing at least one parent and being female relative to the other entity.
-
C.
mainBase
chosen
Indicates that one entity serves as the primary or central base or headquarters for another entity.
-
D.
establishedBase
Indicates that an entity has set up or founded a base or primary operational location in relation to another entity or place.
-
E.
hadBase
Indicates that an entity maintained or operated from a particular base location or primary site.
- 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_69f76ef531ac8190ae6d99e5786e76ec |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fbc995dc2481908b3bd4217f8101e7 |
completed | May 6, 2026, 11:07 p.m. |
| PD | Predicate disambiguation | batch_69fbc8ee04f08190977b7ad70fc85896 |
completed | May 6, 2026, 11:04 p.m. |
Created at: May 3, 2026, 4:20 p.m.