Triple
T36589870
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | יצחק הרצוג |
E902638
|
entity |
| Predicate | תחילת כהונה כיושב ראש מפלגת העבודה |
P186056
|
FINISHED |
| Object | נובמבר 2013 |
—
|
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: נובמבר 2013 | Statement: [יצחק הרצוג, תחילת כהונה כיושב ראש מפלגת העבודה, נובמבר 2013]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: תחילת כהונה כיושב ראש מפלגת העבודה Context triple: [יצחק הרצוג, תחילת כהונה כיושב ראש מפלגת העבודה, נובמבר 2013]
-
A.
startTimeAsLeaderOfKadima
Indicates the point in time at which an entity begins serving as the leader of Kadima.
-
B.
内大臣在任期間開始
Indicates the time when a person’s tenure in the position of Lord Keeper of the Privy Seal (内大臣) begins.
-
C.
tookOfficeDuring
Indicates that one entity assumed or held an official position within the time period defined by another entity or event.
-
D.
宮内大臣在任期間開始
Indicates the time point at which a person’s term of office as Lord Keeper of the Privy Seal (宮内大臣) begins.
-
E.
termStartAsChancellor
Indicates the date or point in time when an individual begins their term serving in the role of chancellor.
- 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_69f76e6592e88190bac4eb00a46e9df9 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7c83f5960819089610ed39c839678 |
completed | May 3, 2026, 10:12 p.m. |
| PD | Predicate disambiguation | batch_69f7c477a4d481908f52e55b6688f60c |
completed | May 3, 2026, 9:56 p.m. |
| PDg | Predicate description generation | batch_69f7c776b4088190bef550c869da530d |
completed | May 3, 2026, 10:08 p.m. |
Created at: May 3, 2026, 4:11 p.m.