Triple
T12089953
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | שמעון פרס |
E287914
|
entity |
| Predicate | תפקיד מרכזי |
P14496
|
FINISHED |
| Object | אדריכל התעשייה הביטחונית הישראלית |
—
|
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: אדריכל התעשייה הביטחונית הישראלית | Statement: [שמעון פרס, תפקיד מרכזי, אדריכל התעשייה הביטחונית הישראלית]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: תפקיד מרכזי Context triple: [שמעון פרס, תפקיד מרכזי, אדריכל התעשייה הביטחונית הישראלית]
-
A.
hasMainRole
chosen
Indicates that an entity holds the primary or most significant role in relation to another entity or context.
-
B.
laterPrimaryRole
Indicates that an entity assumes a specified primary role at a later time than another role or state in a sequence.
-
C.
hasPrimaryDuty
Indicates that one entity holds the main or most important responsibility or obligation toward another entity or within a specified context.
-
D.
specialRole
Indicates that an entity holds a distinctive or exceptional function, status, or responsibility in relation to another entity or context.
-
E.
peakRole
Indicates the role or position an entity holds at the highest or most prominent point of its activity, status, or performance.
- 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_69d6ab4964708190850585628b287b0c |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d9178ad99c8190a54777b9bbe998bc |
completed | April 10, 2026, 3:30 p.m. |
| PD | Predicate disambiguation | batch_69d915000454819089fee00022055599 |
completed | April 10, 2026, 3:19 p.m. |
Created at: April 8, 2026, 9:48 p.m.