Triple
T34317936
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2015 Israeli legislative election |
E880645
|
entity |
| Predicate | forLegislatureNumber |
P2447
|
FINISHED |
| Object | 20th Knesset |
—
|
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: 20th Knesset | Statement: [2015 Israeli legislative election, forLegislatureNumber, 20th Knesset]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: forLegislatureNumber Context triple: [2015 Israeli legislative election, forLegislatureNumber, 20th Knesset]
-
A.
legislatureNumber
chosen
Indicates the specific numbered session or term of a legislative body associated with an entity or event.
-
B.
congressionalNumber
Indicates the specific numbered session or term of a legislative congress to which an entity is associated.
-
C.
numberOfLegislatures
Indicates the total count of distinct legislatures associated with or relevant to a given entity.
-
D.
legislativeTermNumber
Indicates the ordinal number assigned to a specific legislative term within a sequence of legislative periods.
-
E.
coLegislatureWith
Indicates that two legislative bodies share lawmaking authority within the same political system or jurisdiction.
- 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_69f349b9cd508190a996a616903b3e6d |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f717836f0c8190b4a397bbac37dd09 |
completed | May 3, 2026, 9:38 a.m. |
| PD | Predicate disambiguation | batch_69f7127a2ff08190b77d00963c9df621 |
completed | May 3, 2026, 9:16 a.m. |
Created at: May 1, 2026, 1:57 a.m.