Triple

T4248538
Position Surface form Disambiguated ID Type / Status
Subject Philip the Tetrarch E95786 entity
Predicate foundedCity P4560 FINISHED
Object Julias E219361 NE FINISHED

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: Julias | Statement: [Philip the Tetrarch, foundedCity, Julias]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Julias
Context triple: [Philip the Tetrarch, foundedCity, Julias]
  • A. Julias chosen
    Julias was a city in the ancient region of Gaulonitis, near the Sea of Galilee, known from the Roman and New Testament historical context.
  • B. Iulia
    Iulia is a Latin given name, historically used in ancient Rome and closely associated with the feminine form of the name Julius.
  • C. Lucia
    Lucia is a feminine given name of Latin origin, commonly associated with light and used in various European cultures.
  • D. Livias
    Livias was an ancient town in the region of Perea, east of the Jordan River, known from classical and biblical-era sources.
  • E. Josèphe
    Josèphe is the given name of Marie Josèphe Rose Tascher de La Pagerie, better known as Empress Joséphine, the first wife of Napoleon Bonaparte and the first Empress of the French.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69b3453f759881909b91f01a1e82c036 completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b34e9cb71481909b4baa370193148f completed March 12, 2026, 11:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5a87fdca481908bd2c80b10d0dd3d completed March 14, 2026, 6:27 p.m.
Created at: March 12, 2026, 11:06 p.m.