Triple

T9054495
Position Surface form Disambiguated ID Type / Status
Subject Hadrumetum E216963 entity
Predicate culture P1114 FINISHED
Object Roman E270535 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: Roman | Statement: [Hadrumetum, culture, Roman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Roman
Context triple: [Hadrumetum, culture, Roman]
  • A. Roman
    Roman is a masculine given name of Latin origin that has been borne by numerous historical and contemporary figures across Europe and beyond.
  • B. Römer
    The Römer is Frankfurt am Main’s historic city hall complex, renowned for its distinctive stepped gabled façade and long-standing role as a center of municipal government.
  • C. Romanitas chosen
    Romanitas refers to the cultural, political, and social ideals of “Romanness” that defined Roman identity and civilization across history.
  • D. Rromani
    Rromani refers to the Roma people, an ethnic group of traditionally itinerant communities with origins in the Indian subcontinent and a widespread presence across Europe and beyond.
  • E. Romano
    Romano Mussolini was an Italian jazz pianist and painter, known both for his musical career and for being the son of dictator Benito Mussolini.
  • 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_69ca83d362e88190ae44b4e4dc194209 completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cc7a72e2dc8190a16deff8abe701b1 completed April 1, 2026, 1:52 a.m.
NED1 Entity disambiguation (via context triple) batch_69d0177fb9108190846fe872bb003b08 completed April 3, 2026, 7:39 p.m.
Created at: March 30, 2026, 7:10 p.m.