Triple

T22453557
Position Surface form Disambiguated ID Type / Status
Subject Maximus of Ephesus E555052 entity
Predicate associatedWith P37 FINISHED
Object Pergamum 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: Pergamum | Statement: [Maximus of Ephesus, associatedWith, Pergamum]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pergamum
Context triple: [Maximus of Ephesus, associatedWith, Pergamum]
  • A. Pergamus
    Pergamus is a lesser-known figure in Greek mythology, remembered primarily as a descendant of the Trojan royal line through Neoptolemus.
  • B. Pergam
    Pergam is a small settlement located on Rupat Island in Indonesia’s Riau province.
  • C. Pergamon chosen
    Pergamon was an ancient Greek city in western Asia Minor renowned for its powerful Hellenistic kingdom, monumental acropolis, and influential library and cultural institutions.
  • D. Pergamino
    Pergamino is a city in the Buenos Aires Province of Argentina, known as an important agricultural and commercial center in the Pampas region.
  • E. Library of Pergamon
    The Library of Pergamon was an important ancient Greek library and cultural center in Asia Minor, renowned as a rival to the Library of Alexandria and a major hub of scholarship and manuscript collection.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e11e5113208190ab58c6b595f9d1d0 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15b4d6368819082cafbbd83339fbf completed April 29, 2026, 1:13 a.m.
Created at: April 16, 2026, 8:48 p.m.