Triple

T25596989
Position Surface form Disambiguated ID Type / Status
Subject Macedonian conquest of Egypt E641680 entity
Predicate languageOfAdministrationAfter P54038 FINISHED
Object Greek 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: Greek | Statement: [Macedonian conquest of Egypt, languageOfAdministrationAfter, Greek]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: languageOfAdministrationAfter
Context triple: [Macedonian conquest of Egypt, languageOfAdministrationAfter, Greek]
  • A. languageOfCurrentAdministration
    Indicates the language currently used by the governing or administrative authority in charge.
  • B. laterSecondaryLanguageOfAdministration chosen
    Indicates that one language served as a subsequent or later secondary language used for administrative purposes in relation to another language.
  • C. historicallyDominantLanguageOfAdministrationIn
    Indicates that a language has historically been the primary language used for official governance and administrative functions within a given place or political entity.
  • D. languageOfAwardAdministration
    Indicates the language used to administer, manage, or conduct the award process.
  • E. laterOfficialLanguage
    Indicates that one language became an official language of an entity at a later time than another language.
  • 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_69e75dc60d108190b7e2419e36b0134b completed April 21, 2026, 11:21 a.m.
NER Named-entity recognition batch_69f707f7959881908f037f0d6b1d0c36 completed May 3, 2026, 8:31 a.m.
PD Predicate disambiguation batch_69f700fc274c8190a128593dc7c7abd0 completed May 3, 2026, 8:02 a.m.
Created at: April 21, 2026, 4:28 p.m.