Triple

T18524878
Position Surface form Disambiguated ID Type / Status
Subject Alcidice E452688 entity
Predicate motherOf P120 FINISHED
Object Tyro 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: Tyro | Statement: [Alcidice, motherOf, Tyro]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tyro
Context triple: [Alcidice, motherOf, Tyro]
  • A. Tyro chosen
    Tyro is a figure from Greek mythology, known as the mother of the twins Pelias and Neleus by the god Poseidon.
  • B. Tyros
    Tyros is a coastal town in the traditional Tsakonian region of the eastern Peloponnese in Greece, known for its beaches and local maritime heritage.
  • C. Tyras
    Tyras was an ancient Greek colony and trading port on the northern coast of the Black Sea, near the mouth of the Dniester River.
  • D. Tiron
    Tiron was a medieval monastic site in France that became the motherhouse of the Tironensian Order, an influential Benedictine reform movement.
  • E. Tryano
    Tryano is a luxury department store in Abu Dhabi known for its curated selection of high-end fashion, beauty, and lifestyle brands.
  • 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_69d8d387b5548190aa030dad2cb4947e completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e533914e808190a46638de1ce2d57b completed April 19, 2026, 7:57 p.m.
Created at: April 10, 2026, 11:37 a.m.