Triple

T1126944
Position Surface form Disambiguated ID Type / Status
Subject Roman Kingdom E24740 entity
Predicate firstRuler P3535 FINISHED
Object Romulus E24007 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: Romulus | Statement: [Roman Kingdom, firstRuler, Romulus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Romulus
Context triple: [Roman Kingdom, firstRuler, Romulus]
  • A. Numitor
    Numitor is a legendary king of Alba Longa in Roman mythology, best known as the deposed ruler whose grandsons Romulus and Remus ultimately restored his throne.
  • B. Tatius
    Tatius is a legendary king of the Sabines in Roman mythology, known for co-ruling Rome with Romulus after the abduction of the Sabine women.
  • C. Latinus
    Latinus is a figure from Greek and Roman mythology, often depicted as a king in Italy associated with the early legends surrounding the founding of Rome.
  • D. Romulus and Remus chosen
    Romulus and Remus are the legendary twin brothers of Roman mythology who were raised by a she-wolf and are credited with the origins of Rome.
  • E. Adamo Boari
    Adamo Boari was an Italian-born architect best known for his influential early 20th-century work in Mexico, where he helped shape the country’s monumental public architecture.
  • 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_69a4940712c88190aa244f3fc6070a65 completed March 1, 2026, 7:31 p.m.
NER Named-entity recognition batch_69a4bbdc2718819094f5519ffb56993b completed March 1, 2026, 10:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac59a82bb8819084f77aff9af653c0 completed March 7, 2026, 5 p.m.
Created at: March 1, 2026, 7:44 p.m.