Triple

T22186333
Position Surface form Disambiguated ID Type / Status
Subject Fetiales E548305 entity
Predicate traditionalFounder P8000 FINISHED
Object Numa Pompilius 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: Numa Pompilius | Statement: [Fetiales, traditionalFounder, Numa Pompilius]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Numa Pompilius
Context triple: [Fetiales, traditionalFounder, Numa Pompilius]
  • A. Numa Pompilius chosen
    Numa Pompilius was the legendary second king of Rome, renowned for his wisdom, piety, and for establishing many of Rome’s early religious and legal institutions.
  • B. Rómulo
    Rómulo is a masculine given name of Latin origin, commonly used in Spanish- and Portuguese-speaking countries and derived from the legendary Roman founder Romulus.
  • C. Romulo
    Romulo is a Filipino surname most prominently associated with Carlos P. Romulo, a distinguished diplomat, soldier, journalist, and former president of the United Nations General Assembly.
  • D. Romolo
    Romolo is the middle name of Albert R. Broccoli, the influential American film producer best known for co-producing the James Bond movie series.
  • E. Romolo
    Romolo is a station on Milan's Metro system, serving Line 2 in the city of Milan, Italy.
  • 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_69e11e3e0c7c8190b30d278845e2497e completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f12aa8f178819094d1556df5aee5b9 completed April 28, 2026, 9:46 p.m.
Created at: April 16, 2026, 8:35 p.m.