Triple

T16169198
Position Surface form Disambiguated ID Type / Status
Subject Roma (personification of Rome) E392387 entity
Predicate hasCultTitle P14926 FINISHED
Object Dea Roma E1157541 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: Dea Roma | Statement: [Roma (personification of Rome), hasCultTitle, Dea Roma]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dea Roma
Context triple: [Roma (personification of Rome), hasCultTitle, Dea Roma]
  • A. Dea Roma chosen
    Dea Roma is the personified goddess of the city of Rome and the Roman state, embodying its power, virtues, and imperial identity in ancient Roman religion and art.
  • B. Rumuola
    Rumuola is a prominent urban neighborhood and transport hub in Port Harcourt, Rivers State, Nigeria.
  • C. Horahane Roma
    Horahane Roma are a subgroup of Roma people traditionally associated with Islam and found primarily in regions influenced by the former Ottoman Empire.
  • D. Romee
    Romee is a Dutch fashion model best known for her work as a Victoria’s Secret Angel.
  • E. Romão
    Romão is a Portuguese given name and surname derived from the Latin name Romanus, commonly associated with Roman heritage.
  • 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_69d87f1d32208190942e4e499a80c18c completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e21eb5e6d881908749683091afa90c completed April 17, 2026, 11:51 a.m.
NED1 Entity disambiguation (via context triple) batch_69fff7bb6aac8190a33607abfe9a32d0 completed May 10, 2026, 3:12 a.m.
Created at: April 10, 2026, 5:02 a.m.