Triple

T21369464
Position Surface form Disambiguated ID Type / Status
Subject Sifnos E527013 entity
Predicate capital P234 FINISHED
Object Apollonia 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: Apollonia | Statement: [Sifnos, capital, Apollonia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Apollonia
Context triple: [Sifnos, capital, Apollonia]
  • A. Apollonia chosen
    Apollonia is the main town and administrative center of the Greek island of Siphnos in the Cyclades.
  • B. Apollonia
    Apollonia is an ancient coastal city and archaeological site in present-day Israel, known for its Hellenistic, Roman, and Crusader remains overlooking the Mediterranean Sea.
  • C. Apollonia
    Apollonia is the ancient Greek name of the modern Bulgarian coastal town of Sozopol, historically known as an important Black Sea trading and cultural center.
  • D. Apollonia
    Apollonia was an ancient city in the region of Pisidia, in what is now southwestern Turkey, known as a Hellenistic and later Roman urban center.
  • E. Apollonia
    Apollonia is a settlement within the Municipality of Volvi in the Central Macedonia region of northern Greece, known for its rural character and proximity to Lake Volvi.
  • 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_69e0b51e80808190ba5cb05667af02a9 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e8b0ad04e081908ff02b2ee2bc7485 completed April 22, 2026, 11:27 a.m.
Created at: April 16, 2026, 5:09 p.m.