Triple

T22362965
Position Surface form Disambiguated ID Type / Status
Subject Asini municipality E552824 entity
Predicate containsSettlement P847 FINISHED
Object Drepano 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: Drepano | Statement: [Asini municipality, containsSettlement, Drepano]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Drepano
Context triple: [Asini municipality, containsSettlement, Drepano]
  • A. Drepano chosen
    Drepano is a small coastal village in the Argolis region of Greece, known for its beaches and proximity to the historic town of Nafplio.
  • B. Drepanum
    Drepanum was an ancient town in Bithynia (in modern-day Turkey), later renamed Helenopolis in honor of the Roman Empress Saint Helena.
  • C. Akrini
    Akrini is a village in the municipality of Eordaia in the Kozani regional unit of Western Macedonia, Greece.
  • D. Mandraki
    Mandraki is the main port town and one of the primary settlements on the Greek island of Hydra, known for its traditional architecture and seaside setting.
  • E. Mandraki
    Mandraki is the main town and administrative center of the Greek island of Nisyros, known for its traditional architecture and seaside setting.
  • 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_69e11e4affcc8190ba7c27d29062558d completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f157d513b88190adf2181054c95a0d completed April 29, 2026, 12:59 a.m.
Created at: April 16, 2026, 8:44 p.m.