Triple

T3435508
Position Surface form Disambiguated ID Type / Status
Subject Romana E72441 entity
Predicate nickname P55 FINISHED
Object Romana I E72441 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: Romana I | Statement: [Romana, nickname, Romana I]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Romana I
Context triple: [Romana, nickname, Romana I]
  • A. Romana chosen
    Romana is a highly intelligent and compassionate Time Lady from the Doctor Who universe who serves as one of the Doctor’s most capable and scholarly companions.
  • B. Constantina
    Constantina was a daughter of Roman emperor Constantine the Great who became a prominent imperial noblewoman and Christian figure in the 4th-century Roman Empire.
  • C. Julia Augusta
    Julia Augusta is the honorific name given to Livia Drusilla, the influential wife of Emperor Augustus and a powerful matriarch of the early Roman Empire.
  • D. Antonia Augusta
    Antonia Augusta, better known as Antonia Minor, was a prominent Roman noblewoman of the early Imperial period, daughter of Mark Antony and Octavia Minor and mother of Emperor Claudius.
  • E. Ala II Flavia milliaria
    Ala II Flavia milliaria was a large Roman auxiliary cavalry unit known for its deployment along the Empire’s frontiers, including at the Aalen fort in the province of Raetia.
  • 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_69ad85af50288190a854b76653deee6f completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb9f2e4b4819085336fb539daf3c7 completed March 8, 2026, 6:03 p.m.
NED1 Entity disambiguation (via context triple) batch_69b35481a03c81908fd69da55d81aca3 completed March 13, 2026, 12:04 a.m.
Created at: March 8, 2026, 3:16 p.m.