Triple

T21938091
Position Surface form Disambiguated ID Type / Status
Subject Lou-lan E541745 entity
Predicate excavatedBy P7650 FINISHED
Object Aurel Stein 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: Aurel Stein | Statement: [Lou-lan, excavatedBy, Aurel Stein]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Aurel Stein
Context triple: [Lou-lan, excavatedBy, Aurel Stein]
  • A. Aurel Stein chosen
    Aurel Stein was a Hungarian-British archaeologist and explorer renowned for his pioneering expeditions in Central Asia, during which he uncovered important Silk Road manuscripts and archaeological sites.
  • B. Dr. August Stein
    Dr. August Stein was a key Jewish community leader and cultural advocate best known for establishing the Jewish Museum in Prague.
  • C. Ernst Herzfeld
    Ernst Herzfeld was a German archaeologist and Iranologist renowned for his pioneering excavations and research on ancient Persian sites and civilizations.
  • D. Sven Hedin
    Sven Hedin was a Swedish geographer, topographer, and explorer renowned for his expeditions in Central Asia and his detailed mapping of previously uncharted regions.
  • E. George S. Oppenheim
    George S. Oppenheim was an American publisher best known as a founder of the influential publishing house Viking Press.
  • 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_69e0c47e2e5c81909a7f74ce3de50911 completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f1241e35bc81909eb3225d5cd97b92 completed April 28, 2026, 9:18 p.m.
Created at: April 16, 2026, 7:55 p.m.