Triple

T7399888
Position Surface form Disambiguated ID Type / Status
Subject Ehud Olmert E170718 entity
Predicate familyName P18 FINISHED
Object Olmert E170718 NE 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: Olmert | Statement: [Ehud Olmert, familyName, Olmert]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Olmert
Context triple: [Ehud Olmert, familyName, Olmert]
  • A. Ehud Olmert chosen
    Ehud Olmert is an Israeli politician who served as Prime Minister of Israel from 2006 to 2009 and played a central role in peace negotiations with the Palestinians.
  • B. Avigdor
    Avigdor is a Hebrew given name of biblical origin, traditionally used in Jewish communities.
  • C. Tal Rabin
    Tal Rabin is a prominent computer scientist and cryptographer known for her influential work in secure multiparty computation and cryptographic protocols.
  • D. Gila Katsav
    Gila Katsav is an Israeli public figure best known as the wife of former Israeli President Moshe Katsav and for her role as First Lady of Israel during his tenure.
  • E. Moshe Kahlon
    Moshe Kahlon is an Israeli politician known for serving as Israel’s finance minister and for championing socioeconomic reforms, particularly in lowering the cost of living and increasing market competition.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69c68a5f04188190ac266569c9280347 completed March 27, 2026, 1:47 p.m.
NER Named-entity recognition batch_69c6f24dbf288190b8dfea455148841b completed March 27, 2026, 9:10 p.m.
NED1 Entity disambiguation (via context triple) batch_69c81ed378308190b925941415db596d completed March 28, 2026, 6:32 p.m.
Created at: March 27, 2026, 3:10 p.m.