Triple

T21059435
Position Surface form Disambiguated ID Type / Status
Subject Epirotes E518811 entity
Predicate majorSanctuary P5445 FINISHED
Object Dodona 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: Dodona | Statement: [Epirotes, majorSanctuary, Dodona]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dodona
Context triple: [Epirotes, majorSanctuary, Dodona]
  • A. Dodona chosen
    Dodona was an ancient Greek oracle and sanctuary in Epirus, renowned as one of the oldest religious sites dedicated to Zeus.
  • B. Lerna
    Lerna is an ancient region in the Argolid of Greece, famed in mythology as the site of the Lernaean Hydra and important prehistoric settlements.
  • C. Cyllene
    Cyllene is a mountain in the northeastern Peloponnese of Greece, traditionally revered in Greek mythology as the birthplace of the god Hermes.
  • D. Cyllene
    Cyllene is a small, irregular, retrograde moon of Jupiter belonging to the planet’s outer group of distant satellites.
  • E. Delph
    Delph is a historic village in the Saddleworth area of Greater Manchester, England, known for its Pennine landscape and former textile mills.
  • 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_69e0b5053ac48190921529544959e906 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e6fd842e8881909f4ffc4c43b7fa9f completed April 21, 2026, 4:31 a.m.
Created at: April 16, 2026, 2:37 p.m.